Camb.AI Transcription API

Speech-to-text transcription with timestamps.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • 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/camb-ai-transcription-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

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

OpenAPI Specification

camb-ai-transcription-api-openapi.yml Raw ↑
openapi: 3.0.3
info:
  title: Camb.AI Dubbing Transcription API
  description: 'The Camb.AI API provides generative voice AI - text-to-speech, dubbing, translation, voice discovery and cloning, and transcription - powered by the MARS (speech / voice) and BOLI (translation) research models. The REST API is served from https://client.camb.ai/apis and authenticated with an x-api-key header. Most operations are asynchronous: a POST starts a task and returns a task_id, the task is polled with a GET until its status is SUCCESS, and the result (audio, transcript, or translation) is then retrieved. Real-time streaming for TTS, transcription, and speech-to-speech translation is offered over separate public WebSocket channels (see the companion AsyncAPI document). Endpoint paths are grounded in the public documentation at https://docs.camb.ai; request and response schemas below are modeled from the documented parameters and may be simplified.'
  version: '1.0'
  contact:
    name: Camb.AI
    url: https://www.camb.ai
servers:
- url: https://client.camb.ai/apis
  description: Camb.AI production API
security:
- apiKeyAuth: []
tags:
- name: Transcription
  description: Speech-to-text transcription with timestamps.
paths:
  /transcribe:
    post:
      operationId: createTranscription
      tags:
      - Transcription
      summary: Create a transcription task
      description: Transcribes speech to text from an uploaded media file or a media URL, with speaker identification and word-level timestamps.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/TranscriptionRequest'
      responses:
        '200':
          description: Transcription task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreated'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /transcribe/{task_id}:
    get:
      operationId: getTranscriptionStatus
      tags:
      - Transcription
      summary: Poll a transcription task
      description: Returns the status and, when complete, the transcript.
      parameters:
      - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Current transcription task status and result.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskStatus'
        '401':
          $ref: '#/components/responses/Unauthorized'
components:
  schemas:
    Error:
      type: object
      properties:
        message:
          type: string
        code:
          type: string
    TaskCreated:
      type: object
      properties:
        task_id:
          type: string
          description: Identifier used to poll the task.
    TranscriptionRequest:
      type: object
      required:
      - language
      properties:
        language:
          type: string
          description: Locale tag of the audio, for example en-us.
        media_file:
          type: string
          format: binary
          description: Binary audio or video file (MP3, WAV, AAC, FLAC, MP4, MOV, MXF).
        media_url:
          type: string
          description: Media URL to transcribe (alternative to media_file).
        project_name:
          type: string
        project_description:
          type: string
    TaskStatus:
      type: object
      properties:
        status:
          type: string
          description: Task status, for example PENDING, PROCESSING, SUCCESS, or FAILED.
          enum:
          - PENDING
          - PROCESSING
          - SUCCESS
          - FAILED
        run_id:
          type: integer
          description: Present when the task has completed; used to fetch the result.
  responses:
    Unauthorized:
      description: Missing or invalid API key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  parameters:
    TaskId:
      name: task_id
      in: path
      required: true
      description: The task identifier returned when the task was created.
      schema:
        type: string
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key