Skip to main content
POST /v1/data/ai/transcription/run Pricing: Metered: you pay exactly each call’s cost at the selected model’s rates (default OpenAI: Whisper Large V3 Turbo: the model’s own rate).

Request

Send the inputs under params. Only the keys below are accepted; any other key returns 422 invalid_params.
string[]
required
Public URLs of the audio or video files to transcribe, one row per file. Each file is one call to the model.Format e.g. https://www.example.com.
string
default:"openai/whisper-large-v3-turbo"
The speech-to-text model. Pick from the list (popular models first). Each model shows its own rate (per minute of audio, or per 1M tokens), and that is exactly what each call costs.30 allowed values, for example openai/whisper-large-v3-turbo (OpenAI: Whisper Large V3 Turbo), openai/gpt-transcribe (OpenAI: GPT Transcribe), openai/gpt-4o-mini-transcribe (OpenAI: GPT-4o Mini Transcribe), openai/whisper-large-v3 (OpenAI: Whisper Large V3), deepgram/nova-3 (Deepgram: Nova-3), elevenlabs/scribe-v2 (ElevenLabs: Scribe v2), assemblyai/universal-3-6-pro (AssemblyAI: Universal-3.6 Pro), google/gemini-3.5-transcribe (Google: Gemini 3.5 Transcribe), google/chirp-3 (Google: Chirp 3), mistralai/voxtral-small-transcribe-3-0 (Mistral: Voxtral Small Transcribe 3). Fetch the full list with GET /v1/data/ai/transcription?expand=options.
string
The spoken language. Leave empty to detect it automatically.52 allowed values, for example af (Afrikaans), ar (Arabic), bg (Bulgarian), bn (Bengali), ca (Catalan), cs (Czech), cy (Welsh), da (Danish), de (German), el (Greek). Fetch the full list with GET /v1/data/ai/transcription?expand=options.

Example

Response fields

Each row in data is one transcript, keyed by these fields.

Example response

Abridged: long text and lists are shortened.