Speech-to-text Transcription

Velma-2 offers three speech-to-text endpoints. Pick the one that matches your latency, language, and feature needs.

	Batch (multilingual)	Batch English VFast	Streaming
Use case	Transcription with rich metadata	Fast English-only transcription	Real-time transcription
Protocol	HTTP POST	HTTP POST	WebSocket
Languages	Multilingual	English only	Multilingual
Speaker diarization	✓	—	✓
Emotion / accent detection	✓	—	✓
PII/PHI tagging	✓	—	✓

For a side-by-side comparison with the other Velma-2 capabilities, see Which API should I use?.

Authentication

Batch endpoints use the X-API-Key header. Streaming uses an api_key query parameter at connection time. See Authentication and rate limits.

⌘I