ResourcesIntegrationsVoices (Text-to-speech)

Vapi Voices

Our curated selection of high-quality voices

Some legacy voices (Spencer, Neha, Harry, Cole, Paige, Hana, Lily, Kylie) were retired recently. If you were using any of these voices, please review the guide. Learn more →

What are Vapi Voices?

Vapi Voices is our carefully curated selection of high-quality voices designed to simplify your voice AI implementation. We offer a small handful of exceptional voices that you can immediately use in your applications.

Why Choose Vapi Voices?

  • Simple: Skip testing dozens of voices
  • Quality: Each voice is vetted for natural sound
  • Ready to Use: Pre-optimized for your applications
  • Consistent: Reliable quality in all interactions

Vapi Voices V2

We’ve upgraded the text-to-speech model behind Vapi Voices. Version 2 voices sound more realistic, human, and consistent — at a lower cost than the original model.

Version 2 is opt-in per assistant. Your existing assistants are unchanged: if you’re already running a Vapi Voice in production, it keeps behaving exactly as it does today until you choose to upgrade.

To use V2, set version: 2 on your voice configuration through the API or in the Dashboard:

1{
2  "voice": {
3    "provider": "vapi",
4    "voiceId": "Elliot",
5    "version": 2
6  }
7}

Language and multilingual support

Vapi Voices aren’t limited to English. The accent listed for each voice (for example, Canadian or Indian American) describes the voice’s character — not the only language it can speak. Any Vapi Voice can speak a range of languages, set through the language field on your voice configuration.

How multilingual works depends on the voice version:

  • Version 2 supports 40+ languages and defaults to automatic language detection. Leave language unset (or set it to auto) and the voice detects and speaks the language of the conversation. You can also pin a single language (for example, es).
  • Version 1 supports 30+ languages, including English, Spanish, French, German, Italian, Portuguese, Hindi, Japanese, Korean, Chinese, Arabic, and Russian. Set language to the code for the language you want (for example, es-ES or hi).
1{
2  "voice": {
3    "provider": "vapi",
4    "voiceId": "Elliot",
5    "version": 2,
6    "language": "auto"
7  }
8}

To always speak one specific language instead of auto-detecting, set language to that language’s code:

1{
2  "voice": {
3    "provider": "vapi",
4    "voiceId": "Savannah",
5    "version": 2,
6    "language": "es"
7  }
8}

For the full set of accepted language codes, see the voice.language field in the Create Assistant API reference.

For a fully multilingual assistant, pair the voice with a transcriber that supports automatic language detection and list the supported languages in your system prompt. See Multilingual support for the end-to-end setup.

Active Voices

These voices are fully supported and recommended for new assistants. The voices below marked V2 support the upgraded version 2 model.

Elliot V2

  • Gender: Male
  • Accent: Canadian
  • Age: 20s
  • Characteristics: Realistic, friendly, professional, soothing
  • Sample Audio:

Savannah V2

  • Gender: Female
  • Accent: American (Southern)
  • Age: 20s
  • Characteristics: Realistic, straightforward
  • Sample Audio:

Rohan

  • Gender: Male
  • Accent: Indian American
  • Age: 20s
  • Characteristics: Realistic, bright, energetic
  • Note: Version 2 is not available for this voice

Emma New V2

  • Gender: Female
  • Accent: Asian American
  • Age: 20s
  • Characteristics: Realistic, warm, conversational
  • Sample Audio:

Clara New V2

  • Gender: Female
  • Accent: American
  • Age: 30s
  • Characteristics: Realistic, warm, professional
  • Sample Audio:

Nico New V2

  • Gender: Male
  • Accent: American
  • Age: 20s
  • Characteristics: Realistic, young, casual, natural
  • Sample Audio:

Kai New V2

  • Gender: Male
  • Accent: American
  • Age: 30s
  • Characteristics: Realistic, friendly, relaxed, approachable
  • Sample Audio:

Sagar New V2

  • Gender: Male
  • Accent: Indian American
  • Age: 20s
  • Characteristics: Realistic, steady, professional
  • Sample Audio:

Godfrey New V2

  • Gender: Male
  • Accent: American
  • Age: 20s
  • Characteristics: Realistic, young, energetic
  • Sample Audio:

Neil New V2

  • Gender: Male
  • Accent: Indian American
  • Age: 20s
  • Characteristics: Realistic, clear, professional
  • Sample Audio:

Layla New V2

  • Gender: Female
  • Accent: American
  • Age: 20s
  • Characteristics: Realistic, warm, bright, cheerful
  • Sample Audio:

Sid New V2

  • Gender: Male
  • Accent: American
  • Age: 30s
  • Characteristics: Realistic, laid-back, smooth, deep-toned
  • Sample Audio:

Naina New V2

  • Gender: Female
  • Accent: Indian American
  • Age: 20s
  • Characteristics: Realistic, calm, collected, professional
  • Sample Audio:

How to Use

  1. Select a voice from our Active Voices collection
  2. Integrate it into your assistant or squad
  3. Start creating voice interactions immediately

Common Use Cases

  • Customer service virtual agents
  • Content voiceovers and narration
  • Interactive conversational applications

By choosing Vapi Voices, you can focus on building great applications rather than spending time selecting and testing voices.