ResourcesIntegrationsVoices (Text-to-speech)

Deepgram

Use Deepgram for text-to-speech in Vapi.

Deepgram provides text-to-speech for Vapi voice agents.

You can use Deepgram through Vapi’s default integration, or connect your own account in Integrations.

Supported capability

CapabilityProvider value
Text-to-speechdeepgram

Text-to-speech

Set voice.provider to deepgram and voice.voiceId to a Deepgram Aura voice. Browse and copy a voice’s ID from the Voice Library; the default voice is asteria.

$curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
>  -H "Authorization: Bearer $VAPI_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "voice": { "provider": "deepgram", "voiceId": "asteria" }
>  }'

For additional API configuration options, review the DeepgramVoice fields in the Create Assistant API reference.

Supported models and languages

ModelSupported languages
AuraEnglish
Aura-2English, Spanish, German

Because Deepgram offers more than 12 voices, use the Voice Library to browse every voice currently available to your organization and copy its voiceId. You can also review Deepgram’s voice catalog.

Deepgram speech-to-text

Configure Deepgram for speech-to-text.

Voice providers

Compare every voice provider Vapi supports.