Skip to main content
April 9, 2026
FeatureUpdate
API v0.20.0

Language selection for Nova 3 STT

SLNG-hosted Deepgram Nova 3 STT endpoints accept a language parameter in the WebSocket init config. Supported locales by variant:
  • Englishen, en-au, en-us, en-nz, en-gb, en-in
  • Spanishes, es-us, es-419, es-ar, es-mx, es-es
  • Hindihi, en
  • Multi-languagemulti
The Hindi variant also accepts en, so you can transcribe English audio without switching endpoints. See the Speech-to-Text models page for the full parameter list.

More sample rates for Rime Arcana TTS

Rime Arcana now supports 8, 16, 22.05, 24 (default), 32, 44.1, and 48 kHz. You can match your audio pipeline directly without resampling.

Simplified endpointing parameter

The endpointing parameter on Deepgram STT endpoints now accepts only an integer (milliseconds of silence before finalizing speech). Set it to 0 to disable. Default remains 10.
April 8, 2026
Feature
API v0.19.0

Graceful WebSocket session close

Send { "type": "close" } on any WebSocket connection to shut down cleanly. The server finishes processing remaining audio, then closes. This replaces the previous cancel behavior and works across TTS, STT, and bridges.

Keepalive for STT streams

Send { "type": "keepalive" } on STT WebSocket connections to prevent idle timeouts during pauses. Useful for voice agent sessions where the user goes silent but the connection should stay open.

Endpointing controls for Deepgram Nova STT

Two new parameters on Deepgram Nova STT models for tuning speech segmentation:
  • endpointing — milliseconds of silence before finalizing speech. Set to false to disable. Default: 10.
  • utterance_end_ms — milliseconds of silence between words before an UtteranceEnd event. Range: 200–5000 ms, default: 1000 ms.

India region for Nova 3 Hindi

Deepgram Nova 3 Hindi is now available in ap-south-1 (Mumbai), alongside ap-southeast-2 (Sydney). Use the X-Region-Override header to route to the closest region. See models by region.