Text to speech
with human-like voices

Natural, expressive speech from text in 25+ languages.

Try It Free

View Docs

Eve

Leo

Rex

Sal

Carina

Zagan

Helix

Orion

Luna

Wellness

Support

Soft, empathetic, and soothing.

Fine-grained control

Control emotion, pacing, and emphasis with simple speech tags.

Style tags to control delivery.
REST for long-form audio, WebSocket for real-time streaming.

25+ languages

Every voice speaks 25+ languages with natural intonation.

Voices keep their character across languages.
Switch languages seamlessly.

Human-like, expressive speech

Built on the same stack that powers Grok Voice, Tesla vehicles, and Starlink customer support.

Ranked closest to human on the Vapi Humanness Index.
Podcasts, voiceovers, audiobooks, characters, and support agents.

Vapi Humanness IndexAs of July 10, 2026

Grok Text to SpeechSpaceXAI

Eleven v3ElevenLabs

TTS 1.5 MaxInworld

Sonic 3Cartesia

Simple, transparent pricing

Usage-based billing with no hidden fees.

A fraction of competitors' prices.
Pay for what you use.

Price per 1M characters

Grok Text to SpeechSpaceXAI

$15

TTS 1.5 MaxInworld

$35

Sonic 3Cartesia

$50

Eleven v3ElevenLabs

$100

Clone your voice

Clone a voice from two minutes of speech and use it instantly.

30 free clones to start.
Works with speech tags and all 25+ languages.

Original

Cloned

Speed

Speed up or slow down delivery.

1.25×

0.7×0.85×1×1.25×1.5×

Output formats

MP3, WAV, and raw PCM, plus μ-law and A-law for telephony.

"output_format": {

"codec": "mp3",

"sample_rate": 44100,

"bit_rate": 192000

}

mp3wavpcmμ-lawa-law

Text normalization

Numbers, dates, and symbols read the way they're spoken.

Written

Your total is $1,250, due 6/12 at 3:30 PM.

Spoken

Your total is twelve fifty, due June twelfth at three thirty p.m.

Word timestamps

Character-level start and end times for captions, karaoke highlights, and lip-sync.

Nice0.92s

to1.14s

meet1.22s

you,1.44s

Jane.1.60s

Streaming optimization

Three latency levels trade time-to-first-audio against quality.

Best quality

Fastest

Pronunciation overrides

Spell out how names, brands, and jargon should sound.

Pronunciation3 rules

GIF→/dʒɪf/

nginx→"engine x"

SQL→"sequel

Sample rate

From 8 kHz telephony to 48 kHz studio audio.

Sample rate24 kHz

81622.052444.148

Bit rate

MP3 output from 32 up to 192 kbps.

Bit rate128 kbps

326496128192

Explore the full Grok Voice suite

Speech to Speech

Intelligent, real-time conversations with sub-second latency.

$0.05 / min

Speech to Text

Enterprise-grade transcription for meetings, videos, and more.

$0.10 / hr batch$0.20 / hr streaming

Text to Speech