transcribe capability converts audio to text using state-of-the-art speech recognition.
Providers
Basic Usage
Parameters
string
required
URL to the audio file to transcribe.
string
Base64-encoded audio data (alternative to URL).
string
Language code (e.g., ‘en’, ‘es’, ‘fr’). Auto-detected if omitted.
boolean
Enable speaker diarization (identify different speakers).
Response
Examples
Transcribe a Podcast
Process Meeting Recording
From Base64 Audio
Pricing
Supported Formats
- MP3
- WAV
- M4A
- FLAC
- OGG
- WebM
Language Support
Deepgram supports 30+ languages including:- English (en)
- Spanish (es)
- French (fr)
- German (de)
- Chinese (zh)
- Japanese (ja)