ResourcesIntegrationsVoices (Text-to-speech)

Azure

Use Azure Speech text-to-speech voices in Vapi.

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

You can use Azure through Vapi’s default integration, or connect your own account in Integrations. For Azure OpenAI language models, see Azure OpenAI.

Supported capability

CapabilityProvider value
Text-to-speechazure

Text-to-speech

Set voice.provider to azure and voice.voiceId to a voice. Azure offers many voices, you can browse and copy a voice’s ID from the Voice Library; the default voice is andrew.

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

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

Supported languages

Language is set by the voice you choose. Each Azure neural voice is tied to a specific locale, so selecting a voiceId determines the spoken language. There is no separate language setting for Azure text-to-speech. Browse voices by language and copy a voiceId from the Voice Library.

Azure speech-to-text

Configure Azure for speech-to-text.

Voice providers

Compare every voice provider Vapi supports.