ResourcesIntegrationsVoices (Text-to-speech)

OpenAI

Use OpenAI for text-to-speech in Vapi

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

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

Supported capability

CapabilityProvider value
Text-to-speechopenai

Text-to-speech

Set voice.provider to openai, voice.model to a TTS model (tts-1, tts-1-hd, or gpt-4o-mini-tts), and voice.voiceId to a voice. Browse and copy a voice’s ID from the Voice Library; the default voice is alloy.

curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
  -H "Authorization: Bearer $VAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": { "provider": "openai", "model": "gpt-4o-mini-tts", "voiceId": "alloy" }
  }'

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

Supported languages

OpenAI text-to-speech has no separate language setting. The model speaks the language of the input text.

OpenAI language models

Configure OpenAI for language models.

OpenAI speech-to-text

Configure OpenAI for speech-to-text.

Voice providers

Compare every voice provider Vapi supports.