ResourcesIntegrationsVoices (Text-to-speech)

Rime AI

Use Rime AI text-to-speech voices with your Vapi voice agent.

Rime AI provides streaming text-to-speech models and voices that you can use as a Vapi assistant’s voice.

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

Text-to-speech

Set voice.provider to rime-ai, voice.model to a Rime model, and voice.voiceId to a voice. Rime AI offers many voices and supports voice cloning; 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": "rime-ai",
>      "model": "arcana",
>      "voiceId": "luna",
>      "language": "en"
>    }
>  }'

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

Supported models

ModelModel ID
Arcanaarcana
Mist v2mistv2
Mistmist

Supported languages

Language support depends on the selected model. The following model and language combinations are currently supported by Vapi.

LanguageLanguage codeArcanaMist v2Mist
ArabicarX
EnglishenXXX
FrenchfrXXX
GermandeXXX
HebrewheX
HindihiX
JapanesejaX
PortugueseptX
SinhalasiX
SpanishesXXX
TamiltaX
Voices

Compare every text-to-speech provider Vapi supports.