ffmpeg-micro-com Generate API
The Generate API from ffmpeg-micro-com — 6 operation(s) for generate.
The Generate API from ffmpeg-micro-com — 6 operation(s) for generate.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/ffmpeg-micro-com:ffmpeg-micro-com-generate-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: FFmpeg Micro Generate API
version: 1.0.0
description: 'The FFmpeg Micro API runs FFmpeg for you. Upload a file or point at a URL,
create a transcode or transcription job, poll it, and download the result
from a signed URL.
Getting started:
1. Sign up at https://www.ffmpeg-micro.com and create an API key on the dashboard.
2. Send the key on every request as `Authorization: Bearer `.
3. Create a job with `POST /v1/transcodes` (or `POST /v1/transcribe`), poll
`GET /v1/transcodes/{id}` until `status` is `completed`, then call
`GET /v1/transcodes/{id}/download` for a signed download URL.
Billing is metered per second of input duration. Free accounts start with a
one-time token grant and no card.
This file is the official contract. It is the same spec the API serves at
https://api.ffmpeg-micro.com/openapi.yaml, and the public Postman
workspace is generated from it.'
servers:
- url: https://api.ffmpeg-micro.com
description: Production
tags:
- name: Generate
paths:
/v1/generate/scenes:
post:
summary: Split a narration script into scenes (free)
description: 'Break a script into ordered scenes, each with the narration for that scene (same language as the input) and an English image prompt for it. Free: it is the step you iterate on before committing to paid images and speech. Rate limited to 60 requests per minute per API key.'
security:
- bearerApiKey: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateScenesRequest'
responses:
'200':
description: Scenes
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateScenesResponse'
'400':
description: Invalid input
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'429':
$ref: '#/components/responses/GenerateRateLimited'
'502':
$ref: '#/components/responses/GenerationFailed'
tags:
- Generate
operationId: postV1GenerateScenes
x-operation-id-source: derived
/v1/generate/translate:
post:
summary: Translate an ordered list of narrations (free)
description: Translate scene narrations into another language, preserving count and order, so the images built for the source language can be reused and a re-voice costs speech tokens only. Free; rate limited to 60/min per key.
security:
- bearerApiKey: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateTranslateRequest'
responses:
'200':
description: Translations, same length and order as `texts`
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateTranslateResponse'
'400':
description: Invalid input
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'429':
$ref: '#/components/responses/GenerateRateLimited'
'502':
$ref: '#/components/responses/GenerationFailed'
tags:
- Generate
operationId: postV1GenerateTranslate
x-operation-id-source: derived
/v1/generate/image:
post:
summary: Generate an image (6 or 10 tokens)
description: 'Text to image. Default model `flux-schnell` bills 6 tokens per image. `model: nano-banana` (10 tokens) follows style instructions more faithfully. With `reference_urls` (1–4 https images) the result is an EDIT that keeps the referenced character and product identical — the way to build a consistent storyboard; references force `nano-banana`. Tokens are spent before the provider call and refunded if it fails. Rate limited to 30/min per key.'
security:
- bearerApiKey: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateImageRequest'
responses:
'200':
description: Image generated
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateImageResponse'
'400':
description: Invalid input (charged nothing)
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'402':
$ref: '#/components/responses/InsufficientTokens'
'429':
$ref: '#/components/responses/GenerateRateLimited'
'502':
$ref: '#/components/responses/GenerationFailed'
tags:
- Generate
operationId: postV1GenerateImage
x-operation-id-source: derived
/v1/generate/speech:
post:
summary: Generate speech from text (25 tokens per 1,000 characters)
description: Narration-quality text to speech (ElevenLabs multilingual, 29 languages; the same voice reads every language, so a re-voice keeps the narrator). Billed per character of `text`, pro rata, spent before the call and refunded on provider failure. Rate limited to 30/min.
security:
- bearerApiKey: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateSpeechRequest'
responses:
'200':
description: Speech generated
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateSpeechResponse'
'400':
description: Invalid input (charged nothing)
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'402':
$ref: '#/components/responses/InsufficientTokens'
'429':
$ref: '#/components/responses/GenerateRateLimited'
'502':
$ref: '#/components/responses/GenerationFailed'
tags:
- Generate
operationId: postV1GenerateSpeech
x-operation-id-source: derived
/v1/generate/animate:
post:
summary: Animate an image into a video clip (18 tokens per second)
description: 'Image to video (Kling 2.5 Turbo Pro), 5 or 10 seconds. Asynchronous: the balance is checked, the render is submitted, and the tokens are charged under the returned `id`. Poll `GET /v1/generate/animate/{id}` until `completed` or `failed`; a failed render is refunded on that poll. If the render cannot be charged after submit it is cancelled and the response carries its `id` and `cancelled`. Rate limited to 30/min.'
security:
- bearerApiKey: []
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateAnimateRequest'
responses:
'202':
description: Render queued and charged
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateAnimateQueued'
'400':
description: Invalid input (charged nothing)
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'401':
$ref: '#/components/responses/Unauthorized'
'402':
$ref: '#/components/responses/InsufficientTokens'
'429':
$ref: '#/components/responses/GenerateRateLimited'
'502':
$ref: '#/components/responses/GenerationFailed'
tags:
- Generate
operationId: postV1GenerateAnimate
x-operation-id-source: derived
/v1/generate/animate/{id}:
get:
summary: Poll an animation
description: 'Status of a render you submitted. `queued` / `processing` mean keep polling; `completed` carries the video `url` (a signed URL — download promptly); `failed` means the tokens were refunded. A 503 with `status: unknown` means the provider could not be reached for the moment — the render is untouched and still charged; retry after `retry_after_seconds`. Only your own renders are visible.'
security:
- bearerApiKey: []
parameters:
- name: id
in: path
required: true
schema:
type: string
description: The `id` returned by `POST /v1/generate/animate`
responses:
'200':
description: Render state
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateAnimateStatus'
'401':
$ref: '#/components/responses/Unauthorized'
'404':
description: No render with that id belongs to the caller
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'503':
description: Provider unreachable; the render is unaffected. Retry after `retry_after_seconds`.
headers:
Retry-After:
schema:
type: integer
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateAnimateStatus'
tags:
- Generate
operationId: getV1GenerateAnimateById
x-operation-id-source: derived
components:
schemas:
GenerateTranslateRequest:
type: object
required:
- texts
- language
properties:
texts:
type: array
minItems: 1
maxItems: 20
items:
type: string
maxLength: 2000
language:
type: string
description: ISO 639-1 target language, e.g. `fr`
example: fr
GenerateAnimateQueued:
type: object
properties:
id:
type: string
description: Poll handle for GET /v1/generate/animate/:id
status:
type: string
enum:
- queued
duration:
type: integer
aspect:
type: string
tokens_charged:
type: number
example: 90
GenerateAnimateRequest:
type: object
required:
- image_url
- prompt
properties:
image_url:
type: string
format: uri
description: https start frame
prompt:
type: string
maxLength: 2000
description: What moves and how
duration:
type: integer
enum:
- 5
- 10
default: 5
aspect:
type: string
enum:
- '16:9'
- '9:16'
- '1:1'
default: '16:9'
negative_prompt:
type: string
maxLength: 500
description: What the motion must not introduce
ErrorResponse:
type: object
required:
- error
properties:
error:
type: string
details:
type:
- string
- 'null'
GenerateSpeechResponse:
type: object
properties:
url:
type: string
format: uri
description: mp3
characters:
type: integer
tokens_charged:
type: number
example: 1.16
GenerateImageRequest:
type: object
required:
- prompt
properties:
prompt:
type: string
maxLength: 2000
aspect:
type: string
enum:
- landscape_16_9
- portrait_9_16
- square_1_1
default: landscape_16_9
model:
type: string
enum:
- flux-schnell
- nano-banana
default: flux-schnell
description: Ignored when `reference_urls` is given (references force `nano-banana`)
reference_urls:
type: array
minItems: 1
maxItems: 4
items:
type: string
format: uri
description: https images the result must stay faithful to (a character sheet, a product shot)
seed:
type: integer
minimum: 0
description: Fixed seed for repeatability. Omit for random; `null` is rejected.
GenerateScenesRequest:
type: object
required:
- script
properties:
script:
type: string
maxLength: 20000
description: The narration script, any language
max_scenes:
type: integer
minimum: 1
maximum: 20
default: 6
GenerateScenesResponse:
type: object
properties:
scenes:
type: array
items:
$ref: '#/components/schemas/GenerateScene'
tokens_charged:
type: number
example: 0
GenerateTranslateResponse:
type: object
properties:
texts:
type: array
items:
type: string
language:
type: string
tokens_charged:
type: number
example: 0
GenerateImageResponse:
type: object
properties:
url:
type: string
format: uri
aspect:
type: string
model:
type: string
enum:
- flux-schnell
- nano-banana
tokens_charged:
type: number
example: 6
GenerateAnimateStatus:
type: object
properties:
id:
type: string
status:
type: string
enum:
- queued
- processing
- completed
- failed
- unknown
url:
type: string
format: uri
description: Present when `completed` (signed
expires): null
detail:
type: string
description: Present when `failed`
retry_after_seconds:
type: integer
description: Present when `unknown`
tokens_charged:
type: number
description: 0 after a refund; unchanged while queued/processing/unknown
refund:
type: string
enum:
- failed
description: Present only if a refund could not be recorded
GenerateScene:
type: object
properties:
text:
type: string
description: Narration for this scene
same language as the script: null
image_prompt:
type: string
description: English visual description for an image generator
GenerateSpeechRequest:
type: object
required:
- text
properties:
text:
type: string
maxLength: 2000
voice:
type: string
description: Provider voice name; omit for the default narrator
responses:
InsufficientTokens:
description: Not enough tokens for this call; nothing was charged (for `animate`, `id` and `cancelled` are present if a render had already been submitted)
content:
application/json:
schema:
type: object
properties:
error:
type: string
enum:
- insufficient_tokens
tokens_required:
type: number
id:
type: string
cancelled:
type: boolean
Unauthorized:
description: Missing/invalid API key
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
examples:
example:
value:
error: unauthorized
GenerationFailed:
description: The provider failed; any tokens spent were refunded unless `refund` says otherwise
content:
application/json:
schema:
type: object
properties:
error:
type: string
enum:
- generation_failed
detail:
type: string
tokens_charged:
type: number
refund:
type: string
enum:
- failed
GenerateRateLimited:
description: Per-API-key rate limit exceeded (free routes 60/min, paid routes 30/min); see `x-ratelimit-*` headers
securitySchemes:
bearerApiKey:
type: http
scheme: bearer
bearerFormat: opaque-api-key
externalDocs:
description: Guides and examples
url: https://www.ffmpeg-micro.com/docs