XTTS is a multilingual text-to-speech and voice-cloning model

Clone voice to say text

Generate and convert speech using text and audio inputs

Convert audio voices using models

Generate high-quality speech from text using a prompt audio

Transform voice with custom presets

Generate audio from text using VITS

Generate customized spoken audio from text and voice reference

Convert voice to match another using reference audio

Transform your voice into a singer's

Languages ru,en,zh-cn,ja,de,fr,it,pt,pl,tr,ko,nl,cs,ar,es,hu

Install and run a voice processing application

Clone voices for custom TTS

Generate audio from text with different voices

An end-to-end (e2e) Voice Language Model by Fish Audio.

Generate audio or text-to-speech with voice conversion

Make Custom Voices With KokoroTTS

Transform and generate audio with voice conversion

Find the best ASR model for a language and dataset