AI voice model

XTTS-v2

Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning

audio outputfrom 10 creditsrefunded on failure

Try XTTS-v2 Explore more models

What you'll need

Speaker — Original speaker audio (wav, mp3, m4a, ogg, or flv)

About XTTS-v2

XTTS-v2 is an AI voice model you can run directly in the Percify playground — fill in the inputs and generate right in your browser, or call it programmatically through the Percify API. Each run returns a ready-to-download audio hosted on our CDN, and credits are only charged for successful results.

Run XTTS-v2 now

More AI voice models

View the full catalog

Gemini TTSNatural speech with expressive delivery. Supports two speakers in one take.Chatterbox TurboThe fastest open source TTS model without sacrificing quality.Speech-02-HDText-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Optimized for high-fidelity applications like voiceovers and audiobooks.Speech-02-TurboText-to-Audio (T2A) that offers voice synthesis, emotional expression, and multilingual capabilities. Designed for real-time applications with low latency Zonos 2Voice cloning + text-to-speech — clone a voice from a short sample and make it say anything, multilingual.

ElevenLabs eleven-v3 is a text-to-speech model available as a hosted endpoint; requests cost $0.1 per 1000 characters. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.