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.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/faktry-ai:faktry-ai-audio-api"

All apis

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.

Get an API 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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: faktry Media Audio API
  description: '# faktry Media API


    A comprehensive API for AI-powered media processing including image generation/editing, video creation, audio processing, and PDF manipulation.


    ## Authentication


    All requests must include an `Authorization` header with a Bearer token:


    ```

    Authorization: Bearer

    ```


    Two token types are accepted:


    1. **API Key** (recommended for programmatic access): Tokens are prefixed with `mt_` and can be generated in your account settings. Example: `Authorization: Bearer mt_abc123...`

    2. **Supabase JWT**: The session JWT issued by Supabase auth, used by the web app and desktop client.


    ## Credits & Pricing


    All operations consume credits. Costs vary by operation and model:

    - Basic operations: 1-5 credits

    - AI-powered operations: 5-32 credits depending on model

    - Check individual operation descriptions for exact costs


    ## File Uploads


    - Use `multipart/form-data` for file uploads

    - File parameter names: `file`, `file0`, `file1`, etc. for multiple files

    - Maximum file sizes vary by subscription tier


    ## Async Operations


    Some operations run asynchronously and return a job ID. Poll the job status using the returned `poll_url`.'
  version: 1.0.0
  contact:
    name: Media Tools Support
    email: support@mediatools.com
servers:
- url: https://faktry.ai
  description: Production server
security:
- BearerAuth: []
tags:
- name: Audio
paths:
  /api/media/v1/audio/transcribe:
    post:
      operationId: audio_transcribe
      summary: Transcribe Audio
      description: 'Convert speech in audio files to text using AI transcription


        **Model Costs (credits):**

        - `whisper-1`: 2 credits

        - `elevenlabs/speech-to-text/scribe-v2`: 2 credits

        - `nvidia/nemotron-asr-multilingual/asr`: 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                  - whisper-1
                  - elevenlabs/speech-to-text/scribe-v2
                  - nvidia/nemotron-asr-multilingual/asr
                  description: AI model to use for processing
                language:
                  type: string
                response_format:
                  type: string
                temperature:
                  type: number
                  minimum: 0
                  maximum: 1
                timestamp_granularities:
                  type: string
                file:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - model
              - file
      responses:
        '202':
          description: Job queued for async processing
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/generatespeech:
    post:
      operationId: audio_generatespeech
      summary: Generate Speech (TTS)
      description: 'Create audio from text using AI text-to-speech technology


        **Model Costs (credits):**

        - `gpt-4o-mini-tts`: 3 credits

        - `tts-1`: 3 credits

        - `tts-1-hd`: 5 credits

        - `elevenlabs/tts/eleven-v3`: 3 credits

        - `qwen-3-tts/text-to-speech/1.7b`: 3 credits

        - `qwen-3-tts/voice-design/1.7b`: 3 credits

        - `gemini-tts`: 5 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                  - gpt-4o-mini-tts
                  - tts-1
                  - tts-1-hd
                  - elevenlabs/tts/eleven-v3
                  - qwen-3-tts/text-to-speech/1.7b
                  - qwen-3-tts/voice-design/1.7b
                  - gemini-tts
                  description: AI model to use for processing
                input:
                  type: string
                voice:
                  type: string
                response_format:
                  type: string
                speed:
                  type: number
                  minimum: 0.25
                  maximum: 4
                instructions:
                  type: string
                prompt:
                  type: string
                  description: Text prompt for AI generation
              required:
              - model
              - input
              - prompt
      responses:
        '202':
          description: Job queued for async processing
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/clonevoice:
    post:
      operationId: audio_clonevoice
      summary: Clone Voice
      description: 'Clone a voice from audio samples using AI voice cloning technology


        **Model Costs (credits):**

        - `qwen-3-tts/clone-voice/1.7b`: 5 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                  - qwen-3-tts/clone-voice/1.7b
                  description: AI model to use for processing
                reference_text:
                  type: string
                file:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - model
              - file
      responses:
        '202':
          description: Job queued for async processing
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/generatemusic:
    post:
      operationId: audio_generatemusic
      summary: Generate Music
      description: 'Create music and audio from text descriptions using AI music generation


        **Model Costs (credits):**

        - `minimax-music/v2`: 5 credits

        - `minimax-music/v2.6`: 5 credits

        - `elevenlabs/music/v2.5`: 20 credits

        - `minimax/music-3`: 3 credits

        - `google/lyria-3.5`: 5 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                  - minimax-music/v2
                  - minimax-music/v2.6
                  - elevenlabs/music/v2.5
                  - minimax/music-3
                  - google/lyria-3.5
                  description: AI model to use for processing
                lyrics_prompt:
                  type: string
                sample_rate:
                  type: string
                bitrate:
                  type: string
                format:
                  type: string
                prompt:
                  type: string
                  description: Text prompt for AI generation
              required:
              - model
              - lyrics_prompt
              - prompt
      responses:
        '202':
          description: Job queued for async processing
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/generatesound:
    post:
      operationId: audio_generatesound
      summary: Generate Sound
      description: 'Create speech and sound effects from text using AI


        **Model Costs (credits):**

        - `bytedance/seed-audio-1.0`: 5 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                model:
                  type: string
                  enum:
                  - bytedance/seed-audio-1.0
                  description: AI model to use for processing
                speed:
                  type: number
                  minimum: 0.5
                  maximum: 2
                pitch:
                  type: number
                  minimum: -12
                  maximum: 12
                volume:
                  type: number
                  minimum: 0.5
                  maximum: 2
                sample_rate:
                  type: string
                output_format:
                  type: string
                prompt:
                  type: string
                  description: Text prompt for AI generation
              required:
              - model
              - prompt
      responses:
        '202':
          description: Job queued for async processing
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/convert:
    post:
      operationId: audio_convert
      summary: Convert Audio
      description: 'Convert audio files between different formats like MP3, WAV, OGG, AAC, and M4A


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                format:
                  type: string
                  enum:
                  - mp3
                  - wav
                  - ogg
                  - aac
                  - m4a
                  default: mp3
                  description: Output Format
                bitrate:
                  type: string
                  default: 256k
                  description: Bitrate
                sampleRate:
                  type: number
                  default: 44100
                  description: Sample Rate
                file:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - format
              - bitrate
              - sampleRate
              - file
      responses:
        '200':
          description: Processed audio file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed audio file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/mix:
    post:
      operationId: audio_mix
      summary: Mix Audio
      description: 'Combine multiple audio files into a single track with volume control


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                volume:
                  type: number
                  minimum: 0
                  maximum: 2
                  default: 1
                  description: Volume
                file0:
                  $ref: '#/components/schemas/FileUpload'
                file1:
                  $ref: '#/components/schemas/FileUpload'
                file2:
                  $ref: '#/components/schemas/FileUpload'
                file3:
                  $ref: '#/components/schemas/FileUpload'
                file4:
                  $ref: '#/components/schemas/FileUpload'
                file5:
                  $ref: '#/components/schemas/FileUpload'
                file6:
                  $ref: '#/components/schemas/FileUpload'
                file7:
                  $ref: '#/components/schemas/FileUpload'
                file8:
                  $ref: '#/components/schemas/FileUpload'
                file9:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - volume
              - file0
      responses:
        '200':
          description: Processed audio file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed audio file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/trim:
    post:
      operationId: audio_trim
      summary: Trim Audio
      description: 'Cut audio files to specific start time and duration


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                start:
                  type: number
                  minimum: 0
                  multipleOf: 0.1
                  default: 0
                  description: Start Time (seconds)
                duration:
                  type: number
                  minimum: 0
                  multipleOf: 0.1
                  description: Duration (seconds)
                file:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - start
              - duration
              - file
      responses:
        '200':
          description: Processed audio file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed audio file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/merge:
    post:
      operationId: audio_merge
      summary: Merge Audio
      description: 'Combine multiple audio files sequentially into one file


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file0:
                  $ref: '#/components/schemas/FileUpload'
                file1:
                  $ref: '#/components/schemas/FileUpload'
                file2:
                  $ref: '#/components/schemas/FileUpload'
                file3:
                  $ref: '#/components/schemas/FileUpload'
                file4:
                  $ref: '#/components/schemas/FileUpload'
                file5:
                  $ref: '#/components/schemas/FileUpload'
                file6:
                  $ref: '#/components/schemas/FileUpload'
                file7:
                  $ref: '#/components/schemas/FileUpload'
                file8:
                  $ref: '#/components/schemas/FileUpload'
                file9:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - file0
      responses:
        '200':
          description: Processed audio file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed audio file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/analyze:
    post:
      operationId: audio_analyze
      summary: Analyze Audio
      description: 'Extract duration, format, codec, bitrate, sample rate, channels and file size via FFprobe


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - file
      responses:
        '200':
          description: Processed json file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed json file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/timeline:
    post:
      operationId: audio_timeline
      summary: Audio Timeline
      description: 'Build one audio track from several clips placed at exact start times, with silence in the gaps, optional ducking of music under voice, and loudness normalisation. The input files are the clips, and `tracks` is a JSON array string with one object per file in the same order: [{"start": seconds, "role": "voice"|"music"|"fx", "volume": 0-2, "fade_in": s, "fade_out": s}]. `duration` pads or cuts the result to an exact length. `duck` ("true" or a JSON object string with amount_db, attack_ms, release_ms) lowers every music track while a voice track plays and needs at least one of each. `normalize_lufs` (e.g. -16) is applied once, after mixing and ducking.


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                tracks:
                  type: string
                  description: Tracks (JSON array)
                duration:
                  type: number
                  minimum: 0.1
                  maximum: 900
                  multipleOf: 0.1
                  description: Total Length (seconds)
                duck:
                  type: string
                  description: Duck music under voice
                normalize_lufs:
                  type: number
                  minimum: -50
                  maximum: -5
                  multipleOf: 0.5
                  description: Loudness Target (LUFS)
                format:
                  type: string
                  enum:
                  - mp3
                  - wav
                  - m4a
                  - aac
                  - ogg
                  - flac
                  default: mp3
                  description: Output Format
                sample_rate:
                  type: string
                  enum:
                  - '8000'
                  - '16000'
                  - '22050'
                  - '44100'
                  - '48000'
                  - '96000'
                  default: '44100'
                  description: Sample Rate
                file0:
                  $ref: '#/components/schemas/FileUpload'
                file1:
                  $ref: '#/components/schemas/FileUpload'
                file2:
                  $ref: '#/components/schemas/FileUpload'
                file3:
                  $ref: '#/components/schemas/FileUpload'
                file4:
                  $ref: '#/components/schemas/FileUpload'
                file5:
                  $ref: '#/components/schemas/FileUpload'
                file6:
                  $ref: '#/components/schemas/FileUpload'
                file7:
                  $ref: '#/components/schemas/FileUpload'
                file8:
                  $ref: '#/components/schemas/FileUpload'
                file9:
                  $ref: '#/components/schemas/FileUpload'
              required:
              - tracks
              - duration
              - duck
              - normalize_lufs
              - format
              - sample_rate
              - file0
      responses:
        '200':
          description: Processed audio file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed audio file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /api/media/v1/audio/download:
    post:
      operationId: audio_download
      summary: Download Audio
      description: 'Downloads audio content from a provided URL and converts it to the specified format. Supports SoundCloud, YouTube, Vimeo, Bandcamp, and more.


        **Cost:** 1 credits'
      tags:
      - Audio
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                url:
                  type: string
                  description: Audio URL
                format:
                  type: string
                  enum:
                  - mp3
                  - m4a
                  - ogg
                  - flac
                  - wav
                  default: mp3
                  description: Output Format
              required:
              - url
              - format
      responses:
        '200':
          description: Processed audio file
          content:
            application/octet-stream:
              schema:
                type: string
                format: binary
                description: Processed audio file
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '429':
          description: Rate limit exceeded or insufficient credits
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    JobResponse:
      type: object
      properties:
        job_id:
          type: string
          description: Unique job identifier
        status:
          type: string
          enum:
          - pending
          description: Job status
        poll_url:
          type: string
          description: URL to poll job status
      required:
      - job_id
      - status
      - poll_url
    FileUpload:
      type: string
      format: binary
      description: File to upload
    Error:
      type: object
      properties:
        error:
          type: string
          description: Error message
      required:
      - error
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: mt_<api-key> | supabase-jwt
      description: 'Pass either an mt_-prefixed API key or a Supabase session JWT as the Bearer token. Example: `Authorization: Bearer mt_abc123...`'