Référence API
Générez des vidéos par IA de manière programmatique. Soumettez un prompt, suivez l’avancement et recevez une URL vidéo directe — le tout via REST.
URL de base: https://www.yoh.appLes exemples de code utiliseront l’espace réservé sk_live_YOUR_API_KEY tant que vous n’êtes pas connecté.
Démarrage rapide
Créez votre première vidéo en trois appels API : générer → interroger → télécharger.
Sign in and create a key at API Keys. Choose stories:generate and stories:read for generation and polling, then copy the full key immediately — it is shown only once. Keep it in a server environment variable or secret manager. Your account needs enough credits; creating a key does not add credits.
curl https://www.yoh.app/api/v1/credits \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"Submitting a generation request authorizes its credit charge; API integrations do not need an interactive price confirmation. To check cost first, POST the same body to /api/v1/stories/estimate. Optionally send X-Max-Generation-Credits with your maximum whole-number credits: exceeding it returns HTTP 409 before charging. Use the canonical host shown here; redirects from yoh.app can drop your Authorization header.
curl -X POST https://www.yoh.app/api/v1/stories/generate \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: YOUR_UNIQUE_REQUEST_ID" \
-d '{ "prompt": "A dragon teaches a young knight how to fly", "contentType": "cinematic_story", "aspectRatio": "16:9", "scope": "full", "renderVideo": true }'Replace YOUR_UNIQUE_REQUEST_ID with a unique ID for this operation. Reuse that ID and the identical body when retrying a queued generation request after a network failure. A new ID starts a new operation. Direct image/music requests may return a conflict on replay; inspect the asset before retrying. Poll the returned job every 20 seconds until completed or failed. A failed job is terminal; an error on a queued job can describe an automatic retry. For a text-only draft, use scope: "story" and omit renderVideo.
{
"jobId": "cmnk8wu2q0001q3vpmqv93nmy",
"status": "queued",
"pollUrl": "/api/v1/stories/jobs/cmnk8wu2q0001q3vpmqv93nmy"
}curl https://www.yoh.app/api/v1/stories/jobs/cmnk8wu2q0001q3vpmqv93nmy \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"{
"status": "completed", "progress": 100,
"storyId": "cmnk8xxnx000004lbd7siief7",
"videoUrl": "https://cdn.example.com/video/clip.mp4",
"error": null
}C’est tout. videoUrl est une URL publique que vous pouvez télécharger, diffuser ou partager immédiatement.
Authentification
Toutes les requêtes API doivent inclure votre clé API dans l’en-tête Authorization avec le schéma Bearer.
Authorization: Bearer sk_live_YOUR_API_KEYLes clés API commencent par sk_live_. Vous pouvez créer et gérer vos clés depuis la API Keys page. /api-keys
Gardez vos clés API secrètes. Ne les exposez pas dans du code côté client ni dans des dépôts publics. Si une clé est compromise, révoquez-la immédiatement depuis la page Clés API.
Portées et crédits
Chaque clé API reçoit une ou plusieurs portées qui déterminent les endpoints auxquels elle a accès. La génération du texte d’une Story coûte 55 crédits par tâche ; les portées qui produisent aussi des vidéos de clips ou un rendu final (y compris la portée par défaut, full) les facturent en plus, à l’avance. Les crédits sont remboursés si la tâche échoue après toutes les nouvelles tentatives.
| Portée | Donne accès à |
|---|---|
| stories:generate | POST /api/v1/stories/generate, POST /stories/:id/assets, POST /stories/:id/storyboard, POST /stories/:id/videos, POST /stories/:id/render, POST /stories/:id/clips/:clipId/image, POST /stories/:id/clips/:clipId/video, POST /stories/:id/clips/:clipId/video-edit, POST /stories/:id/characters/:assetId/sheet, POST /stories/:id/soundtrack, POST /stories/:id/assets/:assetId/image, POST /stories/:id/clips/:clipId/regenerate, POST /stories/:id/continue, POST /stories/:id/clips-all, POST /stories/:id/clips/:clipId/grid-reference — and the story-asset edits: PATCH /stories/:id/characters|scenes|items/:assetId. Also implies assets:write and series:write, so keys issued before those scopes existed keep working. |
| stories:read | GET /api/v1/stories, GET /api/v1/stories/:id, GET /api/v1/stories/jobs/:id, GET /api/v1/credits, GET /api/v1/models (the models and visual styles the pickers offer, with durations, resolutions, aspect ratios, reference limits, price hints and retired ids), POST /api/v1/stories/estimate, POST /api/v1/stories/analyze-prompt. Implies series:read and assets:read. |
| stories:write | The clip edits: POST/PATCH /stories/:id/clips, PATCH/DELETE /stories/:id/clips/:clipId, POST /stories/:id/clips/:clipId/duplicate; a hired character's looks: POST /stories/:id/characters/:assetId/hire-looks; starting an episode from your own video: POST /api/v1/series/:id/uploads, POST /stories/:id/upload (GET with stories:read; so is GET /stories/:id/media, every file of a story); and the MCP server's editing tools (POST /api/mcp): clip content and dialogue, timeline moves/trims/captions, freeform overlays, cast and set edits. Spends no credits, so a key with this scope but WITHOUT stories:generate can edit a story and physically cannot pay to generate anything. Implied by stories:generate; implies assets:write. |
| assets:read | GET .../characters, .../scenes, .../items, .../clips, GET .../characters/:assetId/hire-looks, GET /api/v1/series/:id/assets |
| assets:write | POST /api/v1/series/:id/assets, PATCH/DELETE /api/v1/series/:id/assets/:assetId, POST /api/v1/uploads, POST /api/v1/uploads/presign (a one-time PUT URL for an audio, video or image file) |
| series:read | GET /api/v1/series, GET /api/v1/series/:id |
| series:write | POST /api/v1/series, PATCH /api/v1/series/:id |
| social:publish | POST /api/v1/social/publish, GET /api/v1/social/publish/:postId |
| accounts:manage | GET/POST /api/v1/accounts, GET/POST /api/v1/accounts/:accountId/credits. For platforms that serve many customers: provision an account per customer and fund it from your own balance. Implied by nothing — an existing key never gains it. |
Générer une vidéo
Mettre en file une tâche de génération vidéo
/api/v1/stories/generatescope: stories:generateEnvoie un prompt et renvoie immédiatement un jobId. La vidéo est générée de manière asynchrone. Interrogez GET /api/v1/stories/jobs/:jobId pour suivre la progression.
Corps de la requête
| Champ | Type | Statut | Description |
|---|---|---|---|
prompt | string | requis | Description de la Story, 5 000 caractères max. |
aspectRatio | string | optionnel | 16:9, 9:16, 1:1 ou 21:9. Par défaut : 16:9. |
renderVideo | boolean | optionnel | false : renvoie le premier clip IA (rapide, ~10 min). true : assemble tous les clips en un seul MP4 via Remotion (~12–15 min). |
scope | string | optionnel | story (text only) or full (text, images and clip videos; default). Use renderVideo: true with full to include the final MP4 and its render fee. Other values return 400 before charging. For assets, storyboard, videos or render on an existing story, use the separate /api/v1/stories/:storyId endpoints below. |
title | string | optionnel | Nom affiché de la Story. |
contentType | string | optionnel | Catégorie de format de la Story : cinematic_story, news_analysis, persona_channel ou ad_spot. Par défaut : cinematic_story. |
locale | string | optionnel | Code de langue, p. ex. en, zh-TW. Par défaut : en. |
seriesId | string | optionnel | Rattacher à une série existante pour garder des personnages visuellement cohérents. |
assets | array | optionnel | The cast and props for this story — reference assets already in your series library, or attach one-off assets inline. See the table below. |
continuityMode | string | optionnel | With a seriesId: how much of the previous episodes this one carries. episodic_continuous (default) picks up open threads, finale resolves them, one_off_episode keeps series plot out entirely. |
isFinale | boolean | optionnel | Implied by continuityMode: "finale"; you rarely need both. |
allowMultiStory | boolean | optionnel | Let one request split into several episodes when the prompt clearly carries more than one. Default false — N episodes means N charges, so it is opt-in. |
seriesContinuityContext | object | optionnel | Escape hatch. Supplying it replaces the continuity we assemble from your series (open threads plus the last three episode recaps), so an incomplete object produces a weaker episode than sending nothing. Prefer continuityMode. |
assets[] optionnel
This array ATTACHES assets to one generation — it is not where an asset is defined. It carries only what is read inline; the full asset shape (character type and role, voice, scene lighting and mood, item material and condition) lives in the series library, which accepts all of it and which the pipeline reads directly. Reference the library by id rather than restating an asset here. Each entry either references an asset in your series library by seriesAssetId (upload it once via POST /api/v1/series/:seriesId/assets and reuse it forever), or defines a one-off asset inline with type + name. The two forms mix freely in one array. Whatever you attach is described to the writer, and its image is reused instead of a new one being generated — so a character keeps their face and a product keeps its packaging.
| Champ | Type | Description |
|---|---|---|
seriesAssetId | string | Reference an existing library asset. Everything else is optional when this is set. |
type | string | character · scene · item · reference. Required for an inline asset. |
name | string | Required for an inline asset. Also how the writer refers to it — name it in your prompt for it to appear. |
description | string | Overrides the library description for this story only. |
imageUrl | string | Image for an inline asset. Re-hosted on our storage. |
itemType | string | Items only: prop · product · logo. A logo is composited flat, never given 3D depth. |
isHeroProduct | boolean | ad_spot: the advertised product — appears in every clip. Fills heroItemId for you. |
isPrimaryBackground | boolean | news_analysis / persona_channel: the set reused across every shot. ad_spot: the real place (e.g. your shop) used in the shots that name it. Fills primaryBackgroundAssetId for you. |
useAsReferenceFrame | boolean | Use this image as the first frame / reference for image-to-video on clips featuring the asset. |
gender | string | Characters only: surfaced to the writer. |
age | string | Characters only: surfaced to the writer. |
personalityTraits | string[] | Characters only: surfaced to the writer. |
timeOfDay | string | Scenes only, e.g. dusk. |
weather | string | Scenes only, e.g. rain. |
persist | boolean | Accrue an inline asset into the series library so later stories can reference it by id. Default false. |
Characters, scenes and items only enter the story when the prompt names them — attaching a whole series library does not drag its entire cast into every episode. The two pin flags are the exception: a pinned hero product or primary background is guaranteed regardless of whether the script says its name.
globalConfig optionnel
Optional nested object controlling duration, output format, and model selection. Every field has a default; pass only what you want to override. The model fields (videoModel, imageModel, characterImageModel, modelStrategy) may also be passed at the top level as a convenience. Unknown model ids degrade to auto rather than failing the request.
This is a superset of the studio's own controls, not a mirror of them. resolution is the studio's resolution pills (default 720p; the story keeps the value you send and each clip makes what its model can, e.g. Seedance 2.5 up to 1080p, Kling and MiniMax H3 from 720p). qualityTier, modelStrategy and seed are API-only. Two fields are advisory: they are shown to the writer as context but nothing enforces them, and they are marked below.
| Champ | Type | Valeurs | Défaut |
|---|---|---|---|
storyInputMode | string | auto · develop · follow_script (auto decides whether the prompt is an idea to develop or a finished script to follow verbatim) | auto |
durationSec | number | 15–192 (total seconds; about one 8 s clip per 8 s, at least 2 — 16 → 8+8, 20 → 8+6+6; longer content is split into episodes) | 60 |
clipCount | number | 2–24 clips sharing durationSec, 4–12 s each (16 with 4 = 4 × 4 s); a count that does not fit is refused 400. Omitted: about one 8 s clip per 8 s, or the count the prompt names ("in 4 clips") | — |
aspectRatio | string | 16:9 · 9:16 · 1:1 · 21:9 | 16:9 |
resolution | string | 480p · 720p · 1080p | 720p |
pace | string | slow · normal · fast | normal |
structure | string | auto · 3_act · 4_act · montage | auto |
captionStyle | string | standard · words — how dialogue captions show: each line whole, or word by word (TikTok style: a few words at a time, the spoken word highlighted). Change it later with MCP update_caption_settings style | words for 9:16, else standard |
qualityTier | string | draft · balanced · premium (premium selects the advanced model lane) | balanced |
stylePreset | string | auto, or a visual style id (list_style_presets kind visual). An unknown id is refused 400; custom style words go in style.cinematicStyle | auto |
platformTarget | string | ADVISORY — shown to the writer as context; nothing enforces it. youtube · tiktok · instagram · x | youtube |
safetyMode | string | ADVISORY — shown to the writer as context; not a content filter. standard · strict | standard |
seed | string | any string — shared across clips for continuity (API-only) | — |
videoModel | string | a model id, or auto | auto |
videoEditModel | string | video editing only — bytedance/seedance-2.5-video-edit (Seedance 2.5 Video Edit), or auto. The old ids muapi/sd25-video-edit and muapi/sd2-video-edit are still accepted and mean the same model. Omit to keep the existing editing recipe. | auto |
imageModel | string | storyboard frames + scene/item images — a model id, or auto (GPT Image 2.5) | auto |
characterImageModel | string | character portraits, sheets and appearance variants — auto (GPT Image 2.5), google/nano-banana-2 or bytedance/seedream-5-pro (list_models: character) | auto |
modelStrategy | string | auto · fixed · cost_optimized · quality_first · hero_premium | auto |
generationMode | string | DEPRECATED — ignored. The selected model determines frame or reference inputs. | auto |
locale | string | en · zh-TW · ja · ko · th · id (also accepted top-level) | en |
contentTypeConfig optionnel
Optional per-contentType creative controls. Fields are validated against the selected content type; omitted fields fall back to sensible defaults. Pass the object matching your contentType. The two pin ids below are usually easier to set as isHeroProduct / isPrimaryBackground on an assets[] entry — an id you write here wins if you send both.
| contentType | Champs |
|---|---|
| cinematic_story | (no per-type fields — format craft is built in) |
| news_analysis | primaryBackgroundAssetId, primaryBackgroundName (pin a studio scene across anchor shots) |
| persona_channel | primaryBackgroundAssetId, primaryBackgroundName (pin the persona's set) |
| ad_spot | heroItemId, heroProductName, heroTagline, heroKeyBenefit, primaryBackgroundAssetId, primaryBackgroundName (the advertised product, and optionally the real place it is sold or used). heroItemId is an item of the seriesId series: its name fills an empty heroProductName (the tagline is never invented from its description) and the item joins the story with its picture. An id that is not an item of that series answers 400 hero_item_not_found (allowed lists the series items); heroItemId without seriesId answers 400 hero_item_needs_series. With no hero given, the series item flagged isHeroProduct is used, else the series product the prompt names, else the first product. Other series products join the story only when the prompt names them or a shot shows them. |
Autres champs optionnels
| Champ | Type | Description |
|---|---|---|
storyQualityConfig | object | { characterStyle?: "match_story" | "keep_own", characterStyleOverrides?: { [character name or series asset id]: "match_story" | "keep_own" }, directClipImageGeneration?: boolean }. characterStyle (default match_story, or the series default): a cast member whose own look is another style is redrawn in the story style, or keeps its own look. Hired characters always keep their own look. enableStyleAdaptedCharacters is deprecated (false reads as keep_own). |
castArt | boolean | scope "story" only. Default true, as the app: once the text is written, cast art (character sheets and shared backgrounds) starts and is charged automatically. false: draw it yourself with POST /assets. Every clip video needs it (409 ASSETS_REQUIRED otherwise). scope "full" always draws it. |
style | object | Style-consistency overrides: cinematicStyle, era, colorPalette, lightingStyle, filmGrain, lensCharacter, materialEmphasis, styleCategory, negativeHints, stylePreset. |
seriesContinuityContext | object | Series continuity context for episodic generation. Used together with seriesId. |
Fields that aren't part of the selected contentType's schema are silently ignored — cinematic_story takes no per-type fields at all, so pass contentTypeConfig only for ad_spot, news_analysis, or persona_channel.
curl -X POST https://www.yoh.app/api/v1/stories/generate \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A 30s spot for a titanium water bottle that keeps ice for 24h",
"contentType": "ad_spot",
"scope": "full",
"renderVideo": true,
"globalConfig": {
"durationSec": 30,
"resolution": "1080p",
"modelStrategy": "hero_premium"
},
"contentTypeConfig": {
"heroProductName": "Northpeak Flask",
"heroTagline": "Ice, 24 hours later.",
"heroKeyBenefit": "Vacuum-sealed titanium keeps ice frozen for a full day"
}
}'Réponse 202 Accepted
{ "jobId": "cmnk8wu2q0001q3vpmqv93nmy", "status": "queued", "pollUrl": "/api/v1/stories/jobs/..." }Endpoints étape par étape
After generating a story with scope: "story", use these endpoints to generate storyboard images, clip videos, and the final rendered MP4 as separate steps.
/api/v1/stories/:storyId/assetsGenerate the cast and world: character portraits + 2×2 character sheets, plus scene and item images. Run this before /storyboard for the best face consistency. Skips assets that already have images. Runs as the app's Make cast art: a look the series already has is reused for free, and each asset that could not be drawn is refunded on its own. Answers 202 { jobId, runId, runUrl, pollUrl, estimatedCredits }.
/api/v1/stories/:storyId/storyboardGenerate storyboard grid images for all clips. Skips clips that already have images. Runs as the app's missing-stills batch (one run per clip, each refunded on its own if it fails): answers 202 { runId, runUrl, clipsToGenerate, estimatedCredits }; poll GET /api/runs/:runId.
/api/v1/stories/:storyId/videosGenerate video for each clip. Skips clips that already have a video URL. Runs as the app's own Generate All: one clip at a time in story order, each continuing the previous clip's video (parallel: true runs a few at once without that reference), each clip charged, settled and refunded on its own within the batch price. Like Generate All, clipIds narrows it to those clips, and with includeExisting: true they are re-generated even when they have a video. Answers 202 { runId, runUrl, cancelUrl, clipIds, estimatedCredits }: poll GET /api/runs/:runId until it ends (result.results lists each clip); POST /api/v1/runs/:runId/cancel stops it. /clips-all takes the same options.
/api/v1/stories/:storyId/renderStitch all clip videos + music + captions into a final MP4. Every clip of the cut needs its video first: otherwise it answers 409 clips_missing_video with missingVideoClips (clipId, position, title, hasImage) and charges nothing.
Un Clip à la fois
The batch endpoints above only fill in what's missing — /storyboard skips clips that already have an image and /videos skips clips that already have a video. To re-roll a shot you don't like, target it directly. These are the same operations as the editor's per-clip regenerate buttons, and they overwrite whatever that clip already has.
Stories run at the same time. The clip endpoints (image, video, video-edit, regenerate, and the batches /storyboard, /videos, /clips-all) start the app's own run at once, exactly as the clip panel or Generate All would, and follow the app's rule: there is no job queue. Inside a batch clips run one at a time in story order, each continuing the previous clip's video; "parallel": true on /videos or /clips-all trades that continuity for speed (a few clips at once, no previous-clip video; on a single-clip endpoint it is ignored). The same request again (the same Idempotency-Key, or the same body a moment later) answers the run already started instead of charging twice. While an API job works on the story (a scope: "full" generate, a render, a continuation) a clip endpoint answers 409 API_JOB_RUNNING (nothing charged, with activeJobId and activeJobScope): retry when that job finishes. The other way round, a story-wide job (render, generate on an existing story) answers 409 STORY_BUSY (nothing charged, Retry-After) while a clip run is working, whether you or the app started it (activeJobScope app_clip_video or app_clip_image, no job to poll; retry later), or another job runs on the story (with pollUrl). A clip video whose characters have no character sheet yet, or whose background has no picture yet, answers 409 ASSETS_REQUIRED (nothing charged) with missingCharacters, missingScenes and clipIds in the error: make the cast art first (POST /assets). One live video per clip: while a clip's video is still being made (a Generate in the app, another call, a run waiting on a slow provider), a new video or video edit on that clip answers 409 CLIP_VIDEO_IN_PROGRESS (nothing charged, with runId when known): poll that run, then retry. /videos and /clips-all never refuse the whole story for one clip: a clip still being made, whose lines are longer than its video, or with nothing to work from is left out and listed in skipped with its reason (in_progress with runId, dialogue_too_long with code and details such as suggestedDurationSeconds, references_required), not charged; the rest run. When every named clip is left out the start answers that clip's refusal (409 DIALOGUE_LONGER_THAN_VIDEO with its numbers, or CLIP_VIDEO_IN_PROGRESS).
/api/v1/stories/:storyId/clips/:clipId/image(Re)generate the storyboard image for ONE clip. Optional body: prompt (art direction for this shot) and imageModel. Runs as the clip panel's own image run: answers 202 { runId, runUrl, estimatedCredits }; poll GET /api/runs/:runId until it ends, then read result.status and result.imageUrl. The same Idempotency-Key answers with the run it already started.
/api/v1/stories/:storyId/clips/:clipId/video(Re)generate the video for ONE clip. Optional body: videoModel, and the clip panel's pills for this run: durationSeconds (snapped up to a length the model makes) and resolution (one the model makes; GET /api/v1/models). Both are saved on the clip, as the pills save them; the aspect ratio is the story's. POST .../regenerate takes the same two. An unknown videoModel is 400; a model that cannot make the story's aspect ratio, or a duration / resolution the model does not make, is 400 invalid_video_settings with allowed in the error (aspectRatio + videoModel, durationSeconds or resolution) — an explicit pick is refused, never silently changed. A clip whose lines need more seconds than the video would have answers 409 DIALOGUE_LONGER_THAN_VIDEO (nothing charged) with clipId, speechSeconds, videoSeconds and suggestedDurationSeconds in the error: send that durationSeconds, or shorten the lines when it is null. There is no mode to pick. The selected model locks the input mode: frame models use the current clip image as start and the next clip image as end; reference models receive their supported, named image, video and voice references. Missing required clip images are rejected before charging. The final clip uses start-only where supported. Runs as the clip panel's own Generate: answers 202 { runId, runUrl, estimatedCredits, durationSeconds, resolution, aspectRatio, videoModel, requested, adjustments? } (what the run makes, and what was asked); poll GET /api/runs/:runId until it ends, then read result.status. The same Idempotency-Key answers with the run it already started; while an API job works on the clip or story it answers 409 API_JOB_RUNNING.
estimatedCredits) | Scope: stories:generate/api/v1/stories/:storyId/clips/:clipId/regenerateRebuild ONE clip end to end — a fresh storyboard image, then a fresh video from it — as a single run: the app's Generate All over this clip with its still drawn first, so the video never starts against the old image, and a still that does not land leaves the video unstarted (nothing charged for it). The right call after changing a clip's description or cast. Optional body: prompt (art direction for the new image), imageModel, videoModel, and the clip panel's durationSeconds / resolution pills (saved on the clip). Answers 202 { runId, runUrl, estimatedCredits, breakdown, durationSeconds, resolution, aspectRatio, videoModel, requested } (what the clip's video makes, and what was asked); poll GET /api/runs/:runId: result.results[0] is the clip, its image the still.
breakdown | Scope: stories:generate/api/v1/stories/:storyId/clips/:clipId/grid-referenceClip authoring supports description for scene and image context, and optional motionDescription for video movement and timed beats. Video generation uses both. When motion is empty, video generation automatically creates and saves timed motion first. Send null to prepare new motion on the next video run. Draw a multi-panel continuity reference sheet for one clip. The panels are derived from the clip's time beats — an authored beat track when motionDescription carries one, otherwise the beat plan its generation length implies — so the sheet mirrors that shot rather than a fixed set of generic moments. Two panels per beat, snapped to a supported grid layout. Starts a run and answers 202 with runId and runUrl; poll GET /api/runs/:runId until status is terminal, then read result.status: completed with the grid URL in result.imageUrl (also saved on the clip), or failed with result.error (refunded). The balance is checked before the run starts: too few credits answers 402 insufficient_credits, and a start the platform refuses answers 503 workflow_start_failed with nothing charged.
Changed 2026-10-19 (breaking): this endpoint used to answer 200 { gridImageUrl, gridData, creditsCharged } with the finished grid. It now answers 202 { runId, runUrl, status: "queued", creditsQuoted, panels, imageModel } at once. Poll GET /api/runs/:runId (MCP: get_run) every 15–30 s until status is completed, failed, canceled or needs_attention; the grid is result.imageUrl. The same Idempotency-Key answers with the run it already started (deduped: true).
/api/v1/stories/:storyId/assets/:assetId/image/api/v1/stories/:storyId/characters/:assetId/sheetDraw (or redraw) ONE character, scene or item from its description, or re-derive a character's 2×2 reference sheet and portrait crop from its current portrait. Characters are sheet-first: one generation produces the sheet and the portrait together. The answer is the new URLs when the run finishes within the request. A long one (a sheet-first character with a fallback chain) answers 202 { "status": "queued", "runId", "runUrl", "creditsCharged" }: poll GET /api/runs/:runId (runUrl) until status is completed or failed; on completion result.status is the HTTP status the request would have answered and result.body the same JSON (the asset, or { error } with the charge already refunded). The charge is made before the run starts and is settled or refunded by the run either way.
/api/v1/stories/:storyId/characters/:assetId/hire-looks/api/v1/stories/:storyId/characters/:assetId/hire-looksThe looks a hired character brings from its creator: { bookingId, owner, pictures, canChoose, looks: [{ id, kind: "main" | "style" | "look", label, styleId, styleLabel, imageUrl, characterSheetUrl, chosen, imported, clipAssetId }] }. The main sheet always comes; chosen looks are in the episode as ready looks (imported) that never apply on their own: a clip uses one when it is picked for that clip. Names only until the hire is paid (pictures: false), pictures after. POST { lookIds } sets the extra looks to bring (ids from GET; the ones left out are removed) and answers { lookIds, imported, removed, staleClipIds, looks }: clips that used a removed look go back to the usual look and are marked out of date. Free (the looks are included in the character fee); the same as Add (free) / Remove on the hire page. A character that is not hired answers 404 not_hired; an unpaid hire or one without the face 409 looks_not_available. MCP: list_hire_looks, choose_hire_looks.
/api/v1/stories/:storyId/clips-allGenerate every missing clip video, drawing first the still of each clip that has nothing else to reference (no cast, no pictured place or item), as ONE run: the app's Generate All, each such still drawn (as the clip panel's image run) just before its own clip's video. Running /storyboard and /videos separately lets the video pass start while images are still missing. It only fills gaps, so re-running after a partial failure is safe; a still that does not land leaves its clip's video unstarted (nothing charged for it). Answers 202 { runId, runUrl, cancelUrl, imagesToGenerate, videosToGenerate, breakdown }; poll GET /api/runs/:runId.
breakdown | Scope: stories:generate/api/v1/stories/:storyId/continueWrite a NEW storyline branching off an existing clip — an alternative continuation the story keeps alongside the original, which is untouched. Required body: branchFromClipId. Optional prompt (where the story goes) and clipCount (4–24). The new clips and their images are made within the price; video is not, so animating them is a separate, separately-priced step. Runs as the editor's own continuation (a story run): answers 202 { jobId, runId, runUrl, pollUrl }; poll the job (or GET /api/runs/:runId) until it ends. A paid-value price above X-Max-Generation-Credits answers 409 with the quote and starts nothing.
/api/v1/stories/:storyId/rendersThe story's finished videos, newest first, with latestSuccessful called out so a failed render is never mistaken for the current cut. A story keeps every render. Optional ?limit (max 50). Each render has width, height and duration (seconds; API renders), aspectRatio, the story's locale and its fileName (API renders are named <title>_<aspect>_<language>.mp4, e.g. glow-cola_9x16_zh-TW.mp4). API renders run in their own pool (2 at once per account, 3 across accounts) and never take the app's export slots; a render past the pool waits its turn (the job reads queued, phase waiting_for_render_slot).
/api/v1/stories/:storyId/clips/:clipId/video-editRewrite a clip's existing video — video-to-video, so subject, composition and motion carry over. Send one of: prompt (an instruction: "make it night and rainy", "push the camera in slowly"); restyleStyleId (redraw the footage in a style preset, keeping its length); or switchAsset ({ target: { kind: "character" | "scene" | "item", id }, subject: { assetId } | { description }, updateCast? }: put the story's character, place or item named by target into the footage by its picture, in place of subject — an asset of the same kind, or a description of what to replace). restyleStyleId and switchAsset cannot be combined; with either one prompt is optional. Optional resolution (480p, 720p, 1080p — the edit dialog's pill; default the clip's, then the story's, then 720p, as in the editor). The edit keeps the source clip's length (durationSeconds is accepted for old callers and does not change it). The clip must already have a video, and the result becomes a new selectable version rather than replacing the old one. A restyle includes a frame review in its price. Runs as the clip panel's own video edit: answers 202 { runId, runUrl, estimatedCredits, durationSeconds, resolution }; poll GET /api/runs/:runId until it ends, then read result.status. A switch with updateCast (default true) points the clip's cast and speakers at the target when the edit lands.
estimatedCredits is the accepted price | Scope: stories:generate/api/v1/stories/:storyId/clips/:clipId/versionGET lists the clip's versions as its Versions list shows them, newest first, each with kind (generate, regenerate, edit, restyle, switch, version, delivery, upload, image, hire_review), imageUrl / videoUrl, durationSeconds, active and selectable. POST { "generationId" } makes the clip show that version: its media, its delivered length (the old trim is cleared) and a timeline span to match — the clip panel's own switch. Refused with 409 and nothing changed: HIRE_REVIEW_NOT_LIVE, CASTING_STALE, VERSION_HAS_NO_MEDIA, VERSION_NOT_READY or approved_clip_locked. Series editors and a video job's creator may switch, as in the app. MCP: select_clip_version; the clip image's own versions: select_clip_image_version.
/api/v1/stories/:storyId/swap-assetPut one story asset in place of another — a character, an item or a background — in one clip (scope: "clip", clipId) or in every clip that uses it (scope: "story"), keeping the script and other clips; a character's spoken lines are re-voiced in the new character's voice inside the same video step, and its price includes that part (voice: lines, credits; refunded alone when the voice cannot be recorded, and the run answers voice.status: "not_recorded"). Body: { scope, clipId?, assetType: "character" | "item" | "scene", from, to, redo: "image" | "video" | "image_video", wardrobe?, light?, resolution?, steps?, dryRun? }. resolution (480p · 720p · 1080p) sets the video steps; omitted, each clip takes its own default, as the clip panel's edit dialog opens at (the clip's resolution, then the story's, then 720p). Per clip it is the clip panel's Switch asset (.../clips/:clipId/image or .../video-edit with switchAsset), and when each lands the clip's cast and dialogue speakers name the new asset. dryRun: true answers the plan and total without charging; otherwise each clip step is charged its own quoted price as it starts (X-Max-Generation-Credits caps the whole swap) and the answer lists each step's runId (each step is the app's own run: poll GET /api/runs/:runId; an image and a video step of one clip run side by side). Its status is started, partial or failed (409): steps that did not start are in retry.steps (nothing charged for them); resend with the same Idempotency-Key, or a new request with steps: retry.steps, and only those run. A clip where a switch to that asset is already running, in the app or from an earlier call, is listed in skipped (with its runId). Clip image and video-edit also take switchAsset / restyleStyleId directly for one clip. MCP: swap_asset.
/api/v1/stories/:storyId/versionsMake a new version of your story in another language, aspectRatio (16:9, 9:16, 1:1, 21:9) and/or stylePreset. Every clip keeps its media; clips are cropped or fitted to the new frame and text layers re-laid out. A language change finds where each line is spoken and translates the script by itself. A format or style version is free and made at once (201). A language version first answers a quote (200, status: "quote"): translationCredits (the copy dialog's price, charged when the version is made), laterSteps (what the paid steps after it will ask) and a confirmToken; send the same body plus confirmToken to make it, once per token. Over X-Max-Generation-Credits is 409 generation_budget_exceeded, a short wallet 402 insufficient_credits; nothing is made or charged then. Without placement, a version is saved on its own, linked to its episode, and a plain copy of an episode in a story joins it as the next episode ("series" files it as the next episode anyway). Optional clipFormat ({ clipId: "crop" | "fit_blur" | "rerender" }). Stories with hired or licensed characters can't be copied (409, error code hired_episode or licensed_cast); one that uses another creator's character is 409 external_asset. MCP: create_story_version.
/api/v1/stories/:storyId/versionsEvery story made from this one, and from those (versions of versions, up to 3 levels), newest first: language, format and style versions and template recasts. Each has depth (1 = made from this story), parentStoryId, versionOf, kind (language, format, style, copy, template, template_claim), language, aspectRatio, stylePreset, a version status (done, running, attention, ready) and links. MCP: list_story_versions. GET /api/v1/stories/:storyId and the story list carry the same provenance object.
/api/v1/stories/:storyId/versionGET lists what is left in a version, in order — prepare (automatic, free), visual (restyle / AI re-render), voice (re-voice in the new language), framing — each with its status and any failed clips. POST { "step": "visual" | "voice" } returns the price and a hash; POST it again with quoteHash to run it. Clips that fail are refunded one by one; POST again to retry only those. "step": "all" runs everything left with one price. A clip the step can't price or run (an unreadable length, or a re-render at 21:9) is listed in skipped with its code and is not charged. POST { "step": "prepare" } starts a failed prepare step (measure + translate) again for free (202). Refusals are 409 with busy, blocked (wait for the translation), quote_changed or nothing. A charge over X-Max-Generation-Credits is 409 generation_budget_exceeded with nothing charged; the charge counts toward the key's spend.
GET /api/v1/stories/:storyId/version/lines lists every spoken line next to its original, with the seconds it takes to say and the seconds it has; PUT it with { "edits": [{ "clipId", "index", "text" }], "keep": [...], "retake": [...] } to fix lines (retake records a line again with the same words) — a voiced clip re-voices only those lines.
# Regenerate clip 3's image, then its video — the rest of the story is untouched
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/clips/CLIP_ID/image \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"
# Poll GET /api/runs/RUN_ID until completed
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/clips/CLIP_ID/video \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"videoModel":"bytedance/seedance-2.0"}'
# Poll GET /api/runs/RUN_ID until completed → the clip's videoUrl is replacedModification de la Story
Direct the story instead of only re-rolling it: rewrite a shot, retime it, add a beat, reorder, or cut one. These are immediate (no job to poll) and cost no credits. A clip's description provides scene and image context; optional motionDescription provides video choreography. Video uses both — edit the appropriate field, then call that clip's /image or /video to re-shoot it with the new direction. Access follows the editor: anyone with edit access to the story (its owner, a series collaborator with edit rights, a job's creator) may edit it with their own key; others get 404.
/api/v1/stories/:storyId/clips/:clipIdEdit a clip. Send only what you want to change: title, description, motionDescription, stillPrompt (the prompt the clip image is drawn from; null clears it; at most 4000 characters), duration, generationDuration, resolution, transitionStyle, sceneId, characterIds, itemIds, dialogue, audioFx, onScreenText (title cards, taglines and lower thirds shown over the video: [{ text, role: title|tagline|label|other, start, end, position: top|center|bottom|lower_third }]; [] clears it).
Media columns (imageUrl, videoUrl, generation history) are deliberately not writable — those belong to the pipelines. Use the clip's /image and /video endpoints to change them.
It is the editor's own save: new dialogue grows the clip when the speech grew (never shrinks it) and keeps the motion's quotes in step; a changed duration is pinned and held to the story's video model (past its maximum: 400 duration_exceeds_lane with allowed: { min, max, tiers }; within range snapped up to whole seconds, with generationDuration and the timed motion beats moved with it, as the clip panel's duration pill does); the answer, and GET on a clip or the clip list, carries resolutionMade: { target, value, adjusted, reason? } (the asked resolution against what the story's model makes); a visual edit on a clip that has an image or video answers scriptEdit (that media is out of date until you regenerate). Refusals, each 409 with nothing written: CLIP_IN_HIRE (the clip is in an unfinished hire and keeps its hired character; bookingId, characterId), approved_clip_locked (an approved collaboration version), DELIVERY_EDIT_CONFLICT (a delivered take's history), CASTING_STALE (made before the casting changed), story_locked (a job or template run holds the story).
/api/v1/stories/:storyId/clipsInsert a clip. title and description required; place it with afterClipId or beforeClipId (omit both to append). Optional: the PATCH fields, plus storylineId (a branch of this story). Following clips shift down automatically and looks keep starting at their clip. The new clip has no image or video yet. 409 CLIP_WORKSPACE: a clip-hire workspace holds only its hired clip.
/api/v1/stories/:storyId/clips/:clipId/duplicateThe editor's Duplicate: a copy right after the clip with its text, still prompt, cast, items, scene, storyline, dialogue, sound cues, on-screen text and its made image/video with their versions. Later positioned clips move right (shiftedClipIds). MCP: duplicate_clip.
/api/v1/stories/:storyId/clips/:clipId/audio-syncA talking clip's audio sync (its dialogue fitted to the delivered video), the clip panel's own read and actions. GET answers audioFinishing (status: queued, running, ready, needs_review or original; stage, error, errorCode, retryable, warnings, runId), revoice and, for needs_review, a candidate. POST { "action": "retry" | "accept" | "original" | "restore" | "background", "runId"?, "volume"? }: retry resumes a failed sync, accept uses the fitted dialogue a needs_review sync prepared, original plays the video's own audio (reversible), restore goes back to the fitted dialogue and background, background sets the separated background's volume (0–1). 409 with a code when the state does not allow it (story locked, result changed, nothing to retry, re-voice running). MCP: get_audio_sync, fix_audio_sync.
/api/v1/stories/:storyId/clipsReorder. Body: { "clips": [{ "id": "...", "order": 0 }, …] } — send every clip with a contiguous 0-based order. Looks (a running injury, a change of outfit) keep starting at the clip they started at.
/api/v1/stories/:storyId/clips/:clipIdCut a clip; the remaining orders close up. A story keeps at least one clip (400 LAST_CLIP); a clip a storyline branches from stays (409 BRANCH_POINT, with its storylineId); a clip in an unfinished hire stays (409 CLIP_IN_HIRE).
# 1. Rewrite the direction + retime the shot (immediate, free)
curl -X PATCH https://www.yoh.app/api/v1/stories/STORY_ID/clips/CLIP_ID \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"description": "The keeper climbs the stairs as the lamp flickers behind him.",
"duration": 7
}'
# 2. Re-shoot it with the new direction
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/clips/CLIP_ID/image \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/clips/CLIP_ID/video \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"# Step 1: Generate story text (~1-2 min)
curl -X POST https://www.yoh.app/api/v1/stories/generate \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A samurai cat guards a cherry blossom tree","contentType":"cinematic_story","scope":"story"}'
# Poll jobId until completed → get storyId
# Step 2: Generate storyboard images (~3-5 min)
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/storyboard \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"
# Poll until completed
# Step 3: Generate clip videos (~1-3 min per clip)
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/videos \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"
# Poll GET /api/runs/RUN_ID until completed
# Step 4: Render final MP4 (~1-2 min)
curl -X POST https://www.yoh.app/api/v1/stories/STORY_ID/render \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"
# Poll until completed → videoUrlInterroger l’état d’une tâche
Obtenir l’état d’une tâche
/api/v1/stories/jobs/:jobIdscope: stories:readInterrogez cet endpoint après avoir appelé POST /api/v1/stories/generate. Une tâche prend en général 8 à 15 minutes selon la longueur de la Story et l’activation de renderVideo. Nous recommandons d’interroger toutes les 15 à 30 secondes.
Cycle de vie du statut de la tâche
queuedgenerating_storygenerating_assetsgenerating_videosrendering_videocompletedoufailedWhich statuses you see depends on the scope you requested — a story job goes straight from generating_story to completed. A transient failure sends the job back to queued with error set to a retry message; that is not terminal, so treat only completed and failed as final states.
Stop. POST /api/v1/stories/jobs/:jobId/cancel (scope stories:write) stops a job the way the app's Stop does: no further paid step starts, work already sent to the provider finishes and is kept, and everything not delivered is refunded once. It answers { outcome: "cancelled" | "stopping" | "already_finished", status }; stopping means a clip is still in flight, so poll until the job reads cancelled (a final state too). POST /api/v1/runs/:runId/cancel stops a batch run (Generate All, started in the app or by /videos, /clips-all or /regenerate; a clip-images batch such as /storyboard) with the app's own Stop: no more clips start; clips never started are never charged. A single clip run's runId (a clip video, video edit or image) cannot be stopped: it answers 409 not_cancellable, and the run finishes and settles itself (a failure is refunded). MCP: cancel_generation.
Reading a job (changed 2026-10-20). A story job that rendered nothing (no render scope, no renderVideo) answers videoUrl: null; its first clip's video is firstClipVideoUrl, never the finished film. A failed clip image job answers failure { category, reason, message } like a clip video. A failed or cancelled job whose refund has not been settled yet says settlement: "pending". A 402 insufficient_credits carries required, balance and topUpUrl.
Champs de la réponse
| Champ | Type | Description |
|---|---|---|
jobId | string | Identifiant unique de la tâche. |
status | string | Statut actuel. Voir le cycle de vie ci-dessus. |
progress | number | Entier de 0 à 100 indiquant le pourcentage d’avancement. |
storyId | string|null | Renseigné une fois la génération de la Story terminée. Sert à récupérer les éléments. |
renderVideo | boolean | Indique si un MP4 final assemblé a été demandé. |
videoUrl | string|null | URL absolue de la vidéo lorsque le statut est completed. Soit un MP4 assemblé (renderVideo: true), soit la vidéo IA du premier clip (renderVideo: false). |
error | string|null | Message d’erreur lisible. Renseigné en cas d’échec, mais aussi pendant une nouvelle tentative, où le statut revient à queued. Toujours null en cas de succès. |
waitingFor / message | string (optional) | Présent tant qu’une tâche attend le résultat d’un fournisseur (le statut reste queued, error vaut null) : la valeur est "provider" et message indique ce qui est attendu. Continuez à interroger. |
execution | object (optional) | L’exécution Workflow qui porte la tâche : { version, runId, phase, heartbeatAt, status }. Suivez-la sur GET /api/runs/:runId (ou son /stream). Absent sur les anciennes tâches. |
createdAt / startedAt / completedAt | string (ISO) | Horodatages. |
runId / runUrl | string (202 only) | Dans la réponse 202 de chaque lancement de tâche (pas dans cette interrogation) : l’exécution lancée pour la tâche et son URL de statut. Facultatif ; interroger cet endpoint suffit. |
Stories
Stop. POST /api/v1/stories/jobs/:jobId/cancel (scope stories:write) stops a job the way the app's Stop does: no further paid step starts, work already sent to the provider finishes and is kept, and everything not delivered is refunded once. It answers { outcome: "cancelled" | "stopping" | "already_finished", status }; stopping means a clip is still in flight, so poll until the job reads cancelled (a final state too). POST /api/v1/runs/:runId/cancel stops a batch run (Generate All, started in the app or by /videos, /clips-all or /regenerate; a clip-images batch such as /storyboard) with the app's own Stop: no more clips start; clips never started are never charged. A single clip run's runId (a clip video, video edit or image) cannot be stopped: it answers 409 not_cancellable, and the run finishes and settles itself (a failure is refunded). MCP: cancel_generation.
Lister les Stories
/api/v1/storiesscope: stories:readRenvoie une liste paginée de vos Stories.
Paramètres de requête
| Paramètre | Défaut | Description |
|---|---|---|
page | 1 | Numéro de page (≥ 1). |
limit | 20 | Résultats par page (1–100). Capped at 100. |
status | — | Filtrer par statut de Story. |
This is the only endpoint that returns a pagination envelope alongside data:
{
"data": [ { "id": "cmnk9cibl0004q3vpijkqfwl4", "title": "...", "status": "completed" } ],
"pagination": { "page": 1, "limit": 20, "total": 137 }
}Obtenir une Story
/api/v1/stories/:storyIdscope: stories:readRenvoie toutes les métadonnées d’une Story, avec le nombre de ses personnages, scènes, objets et clips.
{
"id": "cmnk9cibl0004q3vpijkqfwl4",
"title": "A robot chef cooks in a futuristic kitchen",
"status": "completed", "aspectRatio": "9:16", "locale": "en",
"counts": { "characters": 3, "scenes": 4, "items": 6, "clips": 6 },
"createdAt": "2026-04-04T11:37:04.662Z"
}Vue d’ensemble des éléments
Une fois la tâche terminée, vous pouvez récupérer tous les éléments générés pour la Story grâce au storyId renvoyé par la tâche. Tous les endpoints d’éléments exigent la portée assets:read.
GET /api/v1/stories/:id/charactersPersonnages : nom, description, rôle, imageUrl, infos de voix
GET /api/v1/stories/:id/scenesScènes : description, timeOfDay, weather, lighting, imageUrl
GET /api/v1/stories/:id/itemsAccessoires / objets : description, significance, imageUrl
GET /api/v1/stories/:id/clipsClips : narration, duration, videoUrl, imageUrl, audioUrl
Personnages
Lister les personnages
/api/v1/stories/:storyId/charactersscope: assets:read{
"data": [{
"id": "char_abc123", "name": "Chef Axon", "role": "protagonist",
"description": "A robot chef with a warm personality",
"imageUrl": "https://cdn.example.com/characters/chef-axon.jpg",
"voiceName": "Neutral-EN", "order": 0
}]
}Clips et vidéos
Lister les clips
/api/v1/stories/:storyId/clipsscope: assets:readChaque clip est un segment de scène avec sa propre vidéo générée par IA, son image fixe et son audio. Toutes les URL sont absolues et publiques.
{
"data": [{
"id": "clip_001", "order": 0, "narration": "In the year 2157...",
"duration": 8,
"videoUrl": "https://cdn.example.com/generated/video/clip1.mp4",
"imageUrl": "https://cdn.example.com/generated/image/clip1.jpg",
"audioUrl": null, "status": "completed"
}]
}Lorsque renderVideo vaut false, le videoUrl de la tâche pointe vers la vidéo du premier clip. Utilisez cet endpoint pour obtenir l’URL de la vidéo de chaque clip.
Bibliothèque d’éléments de la Story
Importez un élément une fois, référencez-le indéfiniment
/api/v1/series/:seriesId/assetsscope: assets:writeIl s’agit de la même bibliothèque que celle utilisée par le panneau des éléments du Studio. Importez un personnage, un arrière-plan, un objet ou une référence de style, conservez l’ID renvoyé et référencez-le lors de la génération en passant cet ID comme seriesAssetId dans le tableau des éléments — plus besoin de générer un nouveau lien d’image par vidéo. Les images que vous transmettez sont ré-hébergées sur notre stockage, ainsi l’ID reste fonctionnel même après l’expiration de votre propre URL d’importation.
| Champ | Type | Description |
|---|---|---|
type | string | character, scene, item, ou reference. |
name | string | Nom d’affichage. C’est aussi la clé utilisée pour la correspondance lors des générations ultérieures. |
imageUrl | string | URL publique de l’image. Vous pouvez aussi envoyer imageBase64. |
itemType | string | Éléments uniquement : accessoire, produit ou logo. Un logo est incrusté à plat, sans profondeur 3D. |
isHeroProduct | boolean | Éléments uniquement : le produit concerné par cette publicité. Il apparaît dans chaque Clip. |
isPrimaryBackground | boolean | Scènes uniquement : le studio ou décor réutilisé dans chaque plan fixe. |
seriesDuplicate | string | Personnages uniquement, après avoir demandé à l’utilisateur : « new » ajoute un second personnage avec un nom déjà présent dans la Story. |
- Envoyez un seul élément, ou un tableau « assets » pour en mettre à jour jusqu’à 100 à la fois.
- Par défaut, les éléments fusionnent si le nom correspond exactement, l’importation répétée du même catalogue est donc idempotente — sauf pour un personnage dont le nom existe déjà dans la Story : cela renvoie une erreur 409 SERIES_NAME_EXISTS avec le personnage existant, rien n’est sauvegardé. Demandez à l’utilisateur, puis envoyez seriesDuplicate "new" pour en ajouter un second, ou passez ?mergeStrategy=exact pour mettre à jour l’existant. ?mergeStrategy=fuzzy tolère les renommages ; insert crée toujours un nouvel élément.
- DELETE renvoie une erreur 409 SERIES_ASSET_IN_USE avec les épisodes qui utilisent encore l’élément (stories : id, titre, clipCount) et ne supprime rien. Demandez à l’utilisateur, puis envoyez confirm: true (corps ou ?confirm=true) : les épisodes conservent leur propre copie et leurs clips ne changent pas. Un personnage faisant l’objet d’un recrutement en cours renvoie 409 SERIES_ASSET_HIRED (hires) et ne peut pas être supprimé tant que le recrutement n’est pas terminé.
- Définissez isHeroProduct sur un objet (ad_spot) ou isPrimaryBackground sur une scène (news_analysis / persona_channel) pour l’épingler. Lors de la génération, l’épingle est résolue automatiquement — vous n’avez jamais besoin d’écrire heroItemId manuellement.
| Portée | Donne accès à |
|---|---|
GET | /api/v1/series |
POST | /api/v1/series |
GET | /api/v1/series/:seriesId |
PATCH | /api/v1/series/:seriesId |
GET | /api/v1/series/:seriesId/assets?type=character |
POST | /api/v1/series/:seriesId/assets |
PATCH | /api/v1/series/:seriesId/assets/:assetId |
DELETE | /api/v1/series/:seriesId/assets/:assetId |
DELETE | /api/v1/series/:seriesId/assets/:assetId/looks/:lookId |
POST | /api/v1/series/:seriesId/assets/:assetId/looks/:lookId |
POST | /api/v1/uploads |
PATCH | /api/v1/stories/:storyId/characters/:assetId |
PATCH | /api/v1/stories/:storyId/scenes/:assetId |
PATCH | /api/v1/stories/:storyId/items/:assetId |
POST | /api/v1/stories/estimate |
GET | /api/v1/credits |
GET | /api/v1/models |
POST | /api/v1/stories/:storyId/swap-asset |
POST | /api/v1/series/:seriesId/uploads |
POST | /api/v1/stories/:storyId/upload |
GET | /api/v1/stories/:storyId/upload |
POST | /api/v1/uploads/presign |
GET | /api/v1/stories/:storyId/media |
Start from your own video (MP4, MOV or WebM, up to 1 GB and 10 minutes; free): POST /api/v1/series/:seriesId/uploads makes a draft episode and answers a one-time upload.url that takes one PUT of the file, straight to storage (upload.command is the curl line). Then POST /api/v1/stories/:storyId/upload verifies it, fills an empty title and description from the video, sets its style, picks a cover and cuts it into editable clips; it answers verifying until the check is done, so call it again. GET /api/v1/stories/:storyId/upload reports cutting (with progress) until ready, and links.upload is the page that shows it.
curl -X POST https://www.yoh.app/api/v1/series/series_abc/uploads \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"fileName":"trip.mp4"}'
# → { "storyId": "story_123", "upload": { "url": "https://…", "command": "curl --fail-with-body -sS -X PUT -T <path-to-video> '…'" }, "links": { … } }
curl --fail-with-body -sS -X PUT -T ./trip.mp4 "<upload.url>"
curl -X POST https://www.yoh.app/api/v1/stories/story_123/upload \
-H "Authorization: Bearer sk_live_YOUR_API_KEY"
# → { "status": "cutting", "title": "…", "cut": { "progress": 10, … }, "links": { "upload": "…", "workspace": "…" } }End to end — put a brand's logo in an ad, and keep the id for every ad after it:
curl -X POST https://www.yoh.app/api/v1/series \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"title":"Acme brand films","styleGuide":{"cinematicStyle":"clean product cinematography"}}'
# → { "series": { "id": "series_abc", ... } }curl -X POST https://www.yoh.app/api/v1/series/series_abc/assets \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"type": "item",
"name": "Acme Logo",
"itemType": "logo",
"description": "Wordmark, orange on white",
"imageUrl": "https://your-admin.example.com/tmp/logo.png"
}'
# → { "asset": { "id": "series-item-...", "imageUrl": "https://...blob..." } }
# That imageUrl is ours now — your temporary link can expire.curl -X POST https://www.yoh.app/api/v1/stories/generate \
-H "Authorization: Bearer sk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A 30-second spot for the Acme cordless drill",
"contentType": "ad_spot",
"seriesId": "series_abc",
"assets": [
{ "seriesAssetId": "series-item-...", "isHeroProduct": true }
]
}'
# → { "jobId": "...", "pollUrl": "/api/v1/stories/jobs/..." }Step 2 happens once per asset, not once per video. Step 3 repeats forever with the same id — and because the asset is pinned, the logo is guaranteed in every clip even if the script never says its name. To check the cost before committing, POST the same body to /api/v1/stories/estimate.
Éléments de série
Enregistrer l’image d’un personnage pour une série
/api/v1/series-assets/ensure-character-imagescope: assets:writePOST /api/v1/series-assets/ensure-character-image fonctionne toujours et reste inchangé, mais il ne gère que les personnages. Préférez ce point de terminaison.
Importe et conserve une image de référence de personnage pour une série, afin que l’IA garde le même visage et le même style dans toutes les Stories de cette série. Cette opération est idempotent : l’appeler plusieurs fois avec le même nom de personnage ne pose aucun problème.
| Champ | Type | Description |
|---|---|---|
seriesId | string | ID de la série à laquelle rattacher le personnage. |
characterName | string | Nom du personnage (utilisé comme clé unique dans la série). |
imageUrl | string | URL publique de l’image de référence du personnage. |
Comptes gérés
Pour les plateformes qui servent de nombreux clients. Au lieu d’une seule clé et d’une seule réserve de crédits pour tout le monde (où un client très actif épuise le solde des autres et où personne ne sait qui a dépensé quoi), créez un compte par client et alimentez chacun depuis votre propre solde. Vos clients ne s’inscrivent jamais ici et ne nous paient pas : la relation commerciale reste la vôtre.
Créer un compte
/api/v1/accountsscope: accounts:manageexternalId est votre propre identifiant pour le client. Deux appels avec le même identifiant renvoient le compte existant au lieu d’en créer un second : une requête relancée ne pose donc aucun problème. La clé API est renvoyée une seule fois, à la création : nous n’en stockons qu’un hachage et ne pouvons pas la réafficher, alors enregistrez-la dès réception. Un nouveau compte démarre avec un solde nul.
| Champ | Type | Description |
|---|---|---|
externalId | string | Obligatoire. Votre identifiant pour ce client, par exemple un identifiant de tenant. Unique par plateforme. |
name | string | Libellé facultatif, pour vos propres rapports. |
Remplacer la clé d’un compte géré
/api/v1/accounts/:accountId/api-keysscope: accounts:manageSi la clé initiale a été perdue, appelez cet endpoint avec la clé de la plateforme propriétaire et sans corps de requête. Utilisez l’ID du compte ou l’externalId. L’appel révoque de façon atomique les clés précédentes du compte et renvoie une seule fois une nouvelle apiKey (201). Conservez-la en lieu sûr. Répéter cet appel fait de nouveau tourner la clé ; les nouvelles tentatives normales de création de compte ne remplacent jamais une clé qui fonctionne.
Alimenter un compte
/api/v1/accounts/:accountId/creditsscope: accounts:manageTransfère des crédits de votre propre solde vers celui du compte : il s’agit d’un transfert, pas d’un don, vous ne pouvez donc distribuer que ce que vous avez réellement acheté. Renvoie 402 si votre solde ne suffit pas. :accountId accepte notre ID de compte ou votre externalId.
| Champ | Type | Description |
|---|---|---|
amount | integer | Obligatoire. Crédits à transférer. Doit être positif. |
idempotencyKey | string | Passez l’identifiant de votre facture ou de votre période d’abonnement. Un appel relancé ou redélivré renvoie alors le transfert d’origine au lieu d’alimenter le compte deux fois. Relancez avec la même clé, le même destinataire et le même montant. Une relecture ne transfère pas de nouveau les crédits, même si le solde de la plateforme est désormais épuisé. Changer le destinataire ou le montant renvoie 409. Les clés trop longues sont refusées, pas tronquées. |
description | string | Note facultative, affichée des deux côtés du transfert dans l’historique des crédits. |
GET /api/v1/accounts liste vos comptes avec le solde et les dépenses cumulées de chacun ; GET /api/v1/accounts/:accountId/credits en lit un seul. La clé propre d’un compte géré n’a que des portées de génération : elle ne peut jamais créer ni alimenter de comptes elle-même.
Claude Code & Codex (MCP)
Yoh propose un serveur MCP pour que les agents IA (Claude Code, Codex, Claude Desktop ou tout client MCP) puissent créer et modifier des Stories sur votre compte : écrire une nouvelle Story à partir d’une idée, ajouter ses Personnages et générer la vidéo, ou modifier le contenu d’un Clip et les Dialogues, déplacer ou couper des séquences sur la Timeline, et ajouter des superpositions libres. Toute action consommant des Crédits attend votre approbation explicite à chaque fois. Les règles sont les mêmes que dans l’Éditeur web : une modification effectuée depuis le terminal produit exactement le même résultat qu’un glisser-déposer.
Trois façons de l’utiliser
Choisissez celle qui correspond aux outils de votre agent. La skill Yoh ci-dessous enseigne les trois.
- MCP + navigateur (recommandé dans Codex, Claude Code et les applications Claude) L’agent effectue le travail via ces outils MCP et pilote un onglet de navigateur à côté (Claude dans Chrome, le navigateur de Codex) : après chaque étape, il ouvre le lien contenu dans la réponse (le tableau du Script après une nouvelle Story, le panneau du Clip après une vidéo de clip, la liste Tout générer pendant qu’une exécution est en cours, l’Éditeur avancé pour la Timeline et les calques de texte, le MP4 du Rendu) et vérifie le résultat sur la page réelle. Connectez-vous une fois dans ce navigateur avec le même compte que la clé API. MCP et la page partagent les mêmes données : la page de l’Épisode s’actualise quelques secondes après une modification MCP, et l’agent recharge l’Éditeur avancé après un changement de Timeline. Chaque dépense passe par un seul chemin : le devis MCP ou la boîte de dialogue de prix de l’app.
- Navigateur uniquement (pas de clé API) L’agent travaille sur les pages yoh.app dans votre navigateur, comme vous le feriez : Créer → Story, le tableau du Script et le panneau du Clip, l’éditeur de Personnage et son sélecteur de modèle, Tout générer, l’Éditeur avancé, les Versions et l’exportation. Chaque dépense passe par la boîte de dialogue de prix de l’app, et l’agent ne saisit jamais vos coordonnées de paiement ou votre code de connexion.
- MCP uniquement (headless) Pour les scripts, le CI et les agences créant de nombreuses variantes : quote → confirmToken pour chaque dépense, poll get_job / get_run, arrêt avec cancel_generation, création de variantes avec create_story_versions et generate_all_clips, et téléchargement du videoUrl de chaque Rendu terminé. Aucun navigateur n’est requis.
Exemple dans chaque mode : une publicité de 16 secondes au format 9:16 en anglais et en japonais, écrite dans une Story avec son produit, générée, déclinée en version japonaise et rendue deux fois.
Connexion
Recommandé : connectez-vous avec Yoh, sans clé API. Utilisez exactement cette adresse (yoh.app sans www redirige, et la connexion vérifie l’adresse). Dans Claude Code :
claude mcp add --transport http --scope user yoh https://www.yoh.app/api/mcpTapez ensuite /mcp, choisissez yoh, puis Authenticate, connectez-vous à Yoh dans le navigateur qui s’ouvre avec le compte voulu, et approuvez.
Dans Codex (CLI, extension IDE ou app de bureau ChatGPT), ajoutez le serveur et connectez-vous, puis mettez tool_timeout_sec = 300 sous [mcp_servers.yoh] dans ~/.codex/config.toml et redémarrez Codex :
codex mcp add yoh --url https://www.yoh.app/api/mcp
codex mcp login yoh- App de bureau Claude ou claude.ai : Customize → Connectors → + Add → Add custom connector, nommez-le Yoh, collez l’adresse, puis Connect et connectez-vous. Activez-le dans chaque discussion via + → Connectors. Sur les forfaits Team ou Enterprise, un propriétaire l’ajoute d’abord.
- Cursor : ajoutez yoh avec cette adresse dans ~/.cursor/mcp.json, puis connectez-vous quand Cursor le demande.
- ChatGPT : Plugins → + → Add custom MCP server, nommez-le Yoh, collez l’adresse et connectez-vous. Certains forfaits exigent qu’un administrateur autorise les serveurs personnalisés.
Vérifiez : demandez à votre agent d’exécuter get_credits ; il doit afficher votre solde Yoh. Vous pouvez voir et déconnecter les apps connectées dans Paramètres → Clés API → Apps connectées.
Pour que votre agent voie les pages qu’il modifie : Claude Code avec claude --chrome (l’extension Claude in Chrome), l’app de bureau Claude avec le connecteur Claude in Chrome, ou Codex dans l’app de bureau ChatGPT avec son navigateur. Le skill indique à l’agent quand regarder.
Ou utilisez une clé API (scripts, CI, apps sans connexion)
Créez une clé API dans /api-keys. Pour créer de nouvelles Stories et générer de la vidéo, incluez stories:generate ; pour éditer sans dépenser de Crédits, stories:read et stories:write suffisent. Ensuite, dans Claude Code :
claude mcp add --transport http yoh https://www.yoh.app/api/mcp \
--header "Authorization: Bearer sk_live_YOUR_API_KEY"Ou validez une configuration de projet pour que toute l’équipe bénéficie de la connexion à l’ouverture du repo, chaque membre fournissant sa propre clé via env :
{
"mcpServers": {
"yoh": {
"type": "http",
"url": "https://www.yoh.app/api/mcp",
"headers": { "Authorization": "Bearer ${YOH_API_KEY}" },
"timeout": 900000
}
}
}Dans Codex, ajoutez le serveur à ~/.codex/config.toml et définissez YOH_API_KEY dans votre shell :
# export YOH_API_KEY=sk_live_YOUR_API_KEY
[mcp_servers.yoh]
url = "https://www.yoh.app/api/mcp"
bearer_token_env_var = "YOH_API_KEY"
tool_timeout_sec = 300Installer la skill Yoh
La skill enseigne à votre agent comment bien créer et éditer une Story Yoh : commencer dans une série, estimer le prix avant de dépenser, et regarder les Clips avant de les juger. C’est un fichier unique, maintenu à jour avec le serveur. Exécutez la ligne pour votre agent, ou télécharger SKILL.md
# Claude Code
mkdir -p ~/.claude/skills/yoh && curl -fsSL https://www.yoh.app/skills/yoh/SKILL.md -o ~/.claude/skills/yoh/SKILL.md
# Codex
mkdir -p ~/.agents/skills/yoh && curl -fsSL https://www.yoh.app/skills/yoh/SKILL.md -o ~/.agents/skills/yoh/SKILL.mdEnsuite, demandez simplement : « crée une Story de 60 secondes sur une infirmière de nuit qui entend des fantômes », ou « dynamise le rythme de l’Épisode 3 : supprime les blancs, cale les sous-titres sur le tempo et relance le Rendu ». Lancez /mcp dans Claude Code ou Codex pour vérifier la connexion.
Ce que l’agent peut faire
| Outils | Portée | Exemples |
|---|---|---|
| Lire | stories:read | list_stories · get_story · list_story_versions · get_timeline · get_clip · get_job · get_run · get_credits · list_models · get_asset_images · get_soundtrack · list_overlays · get_revoice · get_audio_sync · list_style_presets · list_voices · list_renders · list_audio_assets · estimate_storyget_clip joint l’image du Storyboard et, avec withFrames, des images réelles échantillonnées à partir de la vidéo générée — c’est le seul moyen pour l’agent de voir à quoi ressemble réellement un Clip. get_asset_images fait de même pour le casting, les décors et les accessoires. |
| Template versions | stories:write / stories:read / assets:read | create_template_version · get_template_version · list_template_destinations · list_template_assets · update_template_version · analyze_template_version · get_template_analysis · accept_template_adaptation · quote_template_version · commit_template_version · cancel_template_version · fork_template_versionMap existing or newly created series assets, review wording and language, then create a free draft. REST families: /api/v1/template-version-sessions/:sessionId and /api/v1/template-version-runs/:runId. Template REST OpenAPI schemas and endpoints |
| Template generation ★ | stories:generate | generate_template_versionQuote the run first, show the maximum credits, then confirm. Poll get_template_version for persisted progress and recovery. |
| Créer ★ | stories:generate | create_storyÉcrivez une toute nouvelle Story à partir d’un prompt. estimate_story est gratuit et estime le prix d’un plan complet à l’avance, ce que les devis par action ne peuvent pas faire. Commencez par scope="story" (texte uniquement) plutôt que "full", qui facture immédiatement la vidéo. |
| Start from a video | stories:write / stories:read | upload_video · finish_video_upload · get_video_upload · upload_file · list_story_mediaFree. upload_video makes a draft episode in a series and answers one curl command that sends the local file straight to storage; finish_video_upload verifies it, fills the details from the video, picks a cover and cuts it into editable clips; get_video_upload reports the cut until it is ready. Open links.upload to watch it. upload_file hosts a song, logo or extra footage the same way (for an overlay src or an asset picture); list_story_media lists every file of a story to download and check. |
| Story versions ★ | stories:generate / stories:read | create_story_version · create_story_versions · get_story_version · get_version_translation · edit_version_translation · list_story_versionsA language, format or style version keeps every clip's media. A format or style version is free; a language version's translation is charged when it is created, so it answers a quote first and is made with confirmToken (the copy dialog's price). create_story_versions makes many at once the cheap way: each new style or aspect once, then its languages from it after its visual step. create_story_version(s) need stories:generate, edit_version_translation stories:write; the reads need stories:read. The paid steps run with run_story_version_step (stories:generate); its free 'prepare' step restarts a failed translation. |
| Stories | series:read / series:write assets:read / assets:write | list_series · get_series · create_series · update_series · list_series_assets · add_series_asset · update_series_asset · delete_series_asset · remove_series_look · use_series_look_as_mainLe niveau supérieur à une Story : les Personnages, Arrière-plans et le Style partagés qui se transmettent d’un Épisode à l’autre. Joignez une nouvelle Story avec create_story seriesId pour en hériter. |
| Clips & dialogues | stories:write | update_clip · update_clips · set_all_clips · reorder_clips · add_clip · delete_clip · duplicate_clip · reorder_clip · set_clip_duration · select_clip_version · select_clip_image_version · add_dialogue_line · update_dialogue_line · remove_dialogue_line · hide_dialogue_line · add_audio_fx · update_audio_fx · remove_audio_fx · update_story · update_caption_settingsUn Dialogue qui dépasse son Clip augmente automatiquement la durée du Clip. Les modifications de texte ne changent jamais les médias déjà générés. update_clips modifie plusieurs Clips à la fois, chacun avec ses propres valeurs ; set_all_clips applique une valeur unique à chaque Clip et refuse le texte, car une description identique partout aplatit l’Épisode. Les deux rejettent tout le lot si une entrée est incorrecte. reorder_clips définit tout un ordre de passage en un seul appel. |
| Assistant Yoh | stories:write | ask_assistant · apply_assistant · undo_assistantConfiez une demande à l’assistant de Yoh, celui qui se cache derrière « Demander à l’IA » de la page Script et l’agent IA de l’Éditeur. ask_assistant ne fait que proposer : les modifications reviennent sous forme de changements et les étapes payantes sous forme de devis. apply_assistant applique les changements que vous gardez ; une étape payante nécessite également le confirmToken de son devis après accord de l’utilisateur. undo_assistant rétablit ce qu’une exécution appliquée a changé. Chaque tour de ask_assistant coûte quelques Crédits : son coût IA réel, plafonné par un petit devis par tour. |
| Timeline | stories:write | move_clip · resize_clip · trim_clip · reset_clip_timing · close_gaps · set_clip_framing · move_caption · hide_clip_video · pin_dialogue_read · export_clip_to_freeform · export_caption_to_freeform · remove_soundtrackDéplacer un Clip fait glisser tous les Clips suivants ; le redimensionnement ancre le début, donc faire glisser le début est un rognage de tête. Les éléments de la Story ne peuvent pas être supprimés ou scindés — masquez-les ou exportez-les vers un calque libre. |
| Overlays | stories:write | add_overlay · update_overlay · move_overlay · resize_overlay · split_overlay · duplicate_overlay · delete_overlay · delete_freeform_row · upload_mediaDeux calques ne peuvent pas se chevaucher sur une même ligne ; un placement conflictuel est refusé et les lignes libres sont listées. Les médias nécessitent une source https hébergée. |
| Style | stories:write | apply_overlay_preset · set_caption_styleLes préréglages de texte de l’Éditeur, les modèles de sous-titres et environ 32 animations d’entrée/sortie — ainsi l’agent applique ce que le produit propose au lieu d’inventer du CSS. Le style des sous-titres se définit par Réplique de Dialogue. |
| Personnages et décors | stories:write | add_character · update_character · delete_character · add_scene · update_scene · delete_scene · add_item · update_item · delete_item · keep_character_sheetSupprimer un Personnage le retire de chaque Clip. Ses Répliques de Dialogue sont conservées sans locuteur jusqu’à ce que vous choisissiez qui les prononce (update_dialogue_line) ; un rôle avec un visage sous licence ou un recrutement en attente ne peut pas être supprimé. |
| Casting voix | stories:write | set_character_voiceVoix de catalogue filtrées selon la langue de la Story plus les Voix clonées prêtes du compte. Le Casting est gratuit ; un Dialogue déjà interprété conserve la Voix avec laquelle il a été rendu. |
| Changer la voix | stories:write | set_revoice_enabled · select_revoice_take · undo_revoice · fix_audio_syncPasser des nouvelles prises à l’interprétation originale est gratuit et réversible ; les prises sont conservées dans les deux cas. |
| Génération ★ | stories:generate | regenerate_clip · regenerate_clip_image · edit_clip_image · enhance_clip_image · generate_clip_video · edit_clip_video · swap_asset · revoice_clip · regenerate_character_sheet · regenerate_asset_image · generate_all_asset_images · generate_soundtrack · generate_storyboard · generate_all_videos · generate_all_clips · generate_clip_grid_reference · continue_story_from_clip · run_story_version_step · render_storyChaque paire oppose modification et génération : edit_clip_image réécrit l’image actuelle à partir d’une instruction tandis que regenerate_clip_image en dessine une nouvelle ; edit_clip_video est du vidéo-vers-vidéo et conserve le sujet, la composition et le mouvement tandis que generate_clip_video regénère à partir de l’image du Storyboard. enhance_clip_image ajuste les visages pour qu’ils correspondent aux Fiches personnages. regenerate_clip effectue l’image puis la vidéo en une seule tâche — le bon choix après avoir changé la description ou le casting d’un Clip. generate_clip_grid_reference dessine une planche de continuité dont les cases proviennent des temps forts du Clip, et non d’un ensemble fixe de moments génériques. |
| Stop | stories:write | cancel_generationThe app's Stop for a jobId or a batch runId: nothing further starts, work in flight finishes and is kept, the rest is refunded. Free. |
| Hired character looks | assets:read stories:write | list_hire_looks · choose_hire_looksThe creator's looks a hired character brings (main sheet, earlier style sheets, the creator's looks) and which are in the episode; choose_hire_looks adds or removes them, the same as the hire page. Names only until the hire is paid. Free. |
Les dépenses sont doublement sécurisées Un outil ★ ne dépense jamais lors de son premier appel : il renvoie un devis en crédits et un confirmToken signé. L’agent doit vous présenter le devis et ne peut continuer qu’avec votre approbation explicite. De plus, une clé sans stories:generate ne peut physiquement pas dépenser — générez une clé en édition seule avec stories:write si vous voulez un agent de lecture et d’édition.
Comment la sécurité et l’exactitude sont garanties
- Le serveur applique les règles de l’Éditeur (déplacement de diapositives, limites de découpe, pistes de sous-titres, lignes de superposition) et répond à une violation en indiquant la plage autorisée au lieu de brider silencieusement.
- L’agent lit l’ensemble des règles depuis la ressource yoh://guide/timeline, et le prompt /mcp__yoh__edit-story lui donne un flux de travail sécurisé.
- La génération est asynchrone — la plupart des outils renvoient un runId que l’agent interroge avec get_run ; quelques-uns (create_story, render_story, illustration de personnage) renvoient un jobId pour get_job, comme pour l’API REST.
- Définissez un délai d’expiration long dans .mcp.json (par exemple 900000) pour qu’un Rendu n’expire pas côté client.
Vérifiez votre connexion
Un test de fumée est fourni avec le repo. Il utilise le protocole réel, teste les règles et prouve que la barrière de dépense fonctionne — il ne dépense jamais de Crédits, et son unique écriture est annulée :
node scripts/mcp-smoke.mjs --url https://www.yoh.app/api/mcp --key sk_live_YOUR_API_KEY
# read-only variant:
node scripts/mcp-smoke.mjs --url https://www.yoh.app/api/mcp --key sk_live_YOUR_API_KEY --skip-writeGérer les clés API
Les endpoints de gestion des clés API utilisent l’session authentication (cookie de l’utilisateur connecté), pas une clé API. Utilisez l’API Keys page dans le navigateur, ou appelez ces endpoints depuis votre backend avec une session valide. /api-keys
Lister les clés API
/api/v1/api-keysscope: session{
"data": [{
"id": "key_abc123", "name": "Production",
"keyPrefix": "sk_live_7WH3",
"scopes": ["stories:generate", "stories:read", "assets:read"],
"revokedAt": null, "createdAt": "2026-04-03T10:00:00.000Z"
}]
}Créer une clé API
/api/v1/api-keysscope: session// Response — full key shown once
{
"id": "key_abc123",
"key": "sk_live_...",
"name": "My integration",
"keyPrefix": "sk_live_7WH3",
"scopes": ["stories:generate", "stories:read", "assets:read"]
}Révoquer une clé API
/api/v1/api-keys/:idscope: session{ "id": "key_abc123", "revoked": true }Erreurs
HTTP 409 with error.code = generation_budget_exceeded means your optional X-Max-Generation-Credits cap was exceeded. The response includes quote.credits; nothing was charged. Change the request or explicitly raise your budget to retry. A malformed cap returns 400. Other 409 conflicts can mean an idempotency key was reused with different input or work is already running. Template-version generation uses its own persisted quoteId contract; see its OpenAPI reference.
Story create (POST /api/v1/stories/generate and /estimate, MCP create_story / estimate_story) checks the series before pricing: 404 series_not_found when the key's user cannot open that seriesId, 403 series_forbidden when they can open it but may not add episodes to it. Nothing is charged.
Rate limits are per key: 5 generation calls, 60 reads and 60 writes a minute. Each call counts once: an MCP tool call is one call even when it runs several v1 steps, and POST /stories/:id/swap-asset is one generation call for every clip it switches.
La plupart des endpoints renvoient un objet error avec un code lisible par une machine. Certains endpoints spécialisés peuvent renvoyer une erreur sous forme de chaîne ou un code au premier niveau ; vérifiez toujours le statut HTTP.
{ "error": { "code": "insufficient_credits", "message": "...", "status": 402 } }| HTTP | code | Signification |
|---|---|---|
| 401 | unauthorized | Clé API manquante ou invalide. |
| 403 | forbidden | La clé API n’a pas la portée requise. |
| 404 | not_found | La ressource demandée n’existe pas. |
| 400 | bad_request | Corps ou paramètres de requête invalides. |
| 402 | insufficient_credits | Crédits insuffisants pour effectuer l’opération. |
| 429 | rate_limited | Trop de requêtes. Consultez l’en-tête Retry-After. |
| 500 | internal_error | Erreur serveur inattendue. |
Limites de débit : Les endpoints de génération acceptent 5 requêtes par minute et par clé API. Les lectures et les modifications de clips (qui ne consomment pas de crédits) en acceptent 60. Si vous atteignez une limite, la réponse inclut un en-tête Retry-After indiquant le nombre de secondes à attendre. Les tâches en échec (après toutes les nouvelles tentatives) remboursent automatiquement les crédits débités.
Publier sur les réseaux sociaux
Envoyez une vidéo terminée directement vers un compte connecté, afin qu’une automatisation puisse piloter générer → rendu → publier avec un seul identifiant. Connectez d’abord les comptes dans l’app ; ce point de terminaison publie vers ceux-ci.
Publier une vidéo
/api/v1/social/publishscope: social:publishRenvoie 202 avec { postId, status: "publishing" } et importe en arrière-plan : interrogez l’endpoint de statut ci-dessous. Passez wait: true pour bloquer jusqu’à la fin de l’import (cela peut prendre plusieurs minutes). L’URL de la vidéo doit correspondre à un rendu réussi ou à la vidéo d’origine importée pour cette Story. Les flux YouTube sont limités aux adresses publiques et à la limite d’import existante de 512 Mo.
socialAccountIdstringstoryIdstringvideoUrlstringplatformstringcaptionstringyoutubeobjectdurationSecnumberaspectRatiostringfileSizeBytesnumberwaitbooleanInterroger l’état de publication
/api/v1/social/publish/:postIdscope: social:publishCycle de vie :
publishing→published|failed.