Transcribe audio to text

Transcribe audio to text using Whisper. Accepts a URL, base64 string, or binary buffer. Language is auto-detected; pass language (ISO 639-1) to override. Set timestamp_granularities to ["word"] or ["segment"] for timestamped output.

post/api/ai/{project_id}/transcribe

Request

Base URL
https://core.blink.new
URL
https://core.blink.new/api/ai/{project_id}/transcribe
Auth
HTTP bearer

Path parameters

project_idstring required

Example:my-project-123

Unique identifier for the project

Request body

modelstring

languagestring

ISO 639-1 language code

response_format'json' | 'text' | 'srt' | 'verbose_json' | 'vtt'

Response

Audio transcription successful

Example response

{
  "result": {
    "text": "Hello, this is a test of speech synthesis.",
    "transcript": "Hello, this is a test of speech synthesis."
  },
  "metadata": {
    "provider": "google-gemini"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.