Skip to main content
Conversational AI Engine: Create advanced voice apps by combining Agora's real-time audio with powerful conversational AI.

Deepgram

Deepgram provides low-latency text-to-speech with a wide range of voices, optimized for real-time conversational AI applications.

info

This integration is fully supported for use with Conversational AI Engine. While it has completed functional validation, it is newer to the platform, and additional provider-specific edge cases may be identified as usage scales across a broader range of applications and workloads.

Sample configuration​

The following example shows a starting tts parameter configuration you can use when you Start a conversational AI agent.


_9
"tts": {
_9
"vendor": "deepgram",
_9
"params": {
_9
"api_key": "<your_deepgram_key>",
_9
"base_url": "wss://api.deepgram.com/v1/speak",
_9
"model": "aura-2-thalia-en",
_9
"sample_rate": 24000
_9
}
_9
}

caution

The parameters listed on this page are validated for use with Conversational AI Engine. Required parameters must be provided as documented. Any additional parameters are passed through directly to the underlying vendor without validation. For a full list of supported options, refer to the Deepgram TTS documentation.

Key parameters​

paramsrequired
  • api_key stringrequired

    The Deepgram API key used to authenticate requests. Get your API key from the Deepgram Console.

  • model stringrequired

    The identifier of the TTS model to use. See Deepgram voices and languages.

  • base_url stringnullable

    The WebSocket URL for the Deepgram streaming API. Defaults to wss://api.deepgram.com/v1/speak.

  • sample_rate numbernullable

    The audio sampling rate in Hz.