ResourcesIntegrationsVoices (Text-to-speech)

Microsoft

Use Microsoft’s MAI text-to-speech voices for your Vapi voice agent.

Microsoft is a text-to-speech provider you can use for your voice agent’s voice, offering the MAI-Voice-2 voices from Azure AI Speech. This page covers what Microsoft is and how to select a voice.

What is Microsoft

Microsoft provides the MAI-Voice-2 text-to-speech voices through Azure AI Speech. On Vapi, you select a Microsoft voice for an assistant.

You can use Microsoft through Vapi’s default integration, or use your own account by connecting it in Integrations.

Text-to-speech

Set voice.provider to microsoft and voice.voiceId to a voice. Microsoft offers many voices, you can browse and copy a voice’s ID from the Voice Library.

$curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
>  -H "Authorization: Bearer $VAPI_API_KEY" \
>  -H "Content-Type: application/json" \
>  -d '{
>    "voice": { "provider": "microsoft", "voiceId": "en-US-Ethan:MAI-Voice-2" }
>  }'

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

Supported languages

Language is set by the voice you choose. Each Microsoft voice is tied to a specific locale (for example, en-US-Ethan:MAI-Voice-2), so selecting a voiceId determines the spoken language. There is no separate language setting for Microsoft text-to-speech. Browse voices by language and copy a voiceId from the Voice Library.

Voices

Compare every text-to-speech provider Vapi supports.