ResourcesIntegrationsVoices (Text-to-speech)

Hume

Use Hume’s expressive text-to-speech voices for your Vapi voice agent.

Hume is a text-to-speech provider you can use for your voice agent’s voice. Connect Hume to use its Octave voices on a Vapi assistant. This page covers what Hume is and how to select a voice.

What is Hume

Hume is a text-to-speech provider whose Octave models generate expressive, emotionally aware speech. On Vapi, you select a Hume voice for an assistant, and Hume also supports custom voices.

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

Text-to-speech

Set voice.provider to hume, voice.model to a Hume model (octave or octave2), and voice.voiceId to a voice. Hume offers many voices and supports custom 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": "hume", "model": "octave", "voiceId": "VOICE_ID" }
>  }'

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

Voices

Compare every text-to-speech provider Vapi supports.