OpenTypeless

Deepgram Nova-3

Deepgram is usually the fastest path to a stable first STT setup in OpenTypeless.

Official Documentation

Deepgram API Getting Started

Official quickstart and authentication basics.

https://developers.deepgram.com/docs/getting-started-with-the-api

Deepgram Live WebSocket Reference

WebSocket endpoint and live transcription parameters.

https://developers.deepgram.com/reference/listen-live

Get API Key

  1. Create a Deepgram account and open project dashboard.
  2. Create an API key with speech-to-text permissions.
  3. Copy and store the key securely.

Configure in OpenTypeless

  1. Settings > Speech Recognition > Provider: Deepgram.
  2. Paste API key.
  3. Keep language on Auto Detect unless a fixed language is required.
  4. Click Test and verify latency is returned.

Recommended Configuration

OpenTypeless uses Deepgram live WebSocket mode with Nova-3 and smart formatting.

Provider: deepgram
Protocol: WebSocket
Endpoint: wss://api.deepgram.com/v1/listen
Auth header: Authorization: Token <DEEPGRAM_API_KEY>
Model: nova-3
Audio: linear16, 16000 Hz, mono

Operational Tip

💡
If multilingual sessions show unstable punctuation, set a fixed language first and compare before reverting to auto detect.