AI Voice Agents

Home / Voice cloning

F5-TTS

Zero-shot open-source text-to-speech model

F5-TTS is an open-source zero-shot text-to-speech model that clones a voice from a short reference clip. The project publishes code, checkpoints and a research paper.

voice-cloningttszero-shotpython

vs Applio vs Chatterbox vs Descript F5-TTS alternatives

More in Voice cloning

Applio

Voice conversion tool built on RVC

Open sourcevoice-cloningvoice-conversion

Chatterbox

Open-source TTS from Resemble AI

Open sourcevoice-cloningtts

Descript

Audio and video editor with voice cloning

Freemiumvoice-cloningediting

Fish Speech

Open-source TTS and voice cloning models

Open sourcevoice-cloningtts

GPT-SoVITS

Few-shot voice cloning and text-to-speech

Open sourcevoice-cloningtts

OpenVoice

Open-source voice cloning from MyShell and MIT

Open sourcevoice-cloningtts