Best Open-Source Text-to-Speech & Voice Cloning

6 tools found

Coqui TTS

Open-source text-to-speech and voice cloning toolkit replacing ElevenLabs with local, multi-model Python inference across 1,100 languages.

46.2kLinuxmacOSWindows2y ago

MPL-2.0Text-to-Speech & Voice Cloning

Suno Bark

Suno Bark is an open-source text-to-audio model alternative to ElevenLabs that runs locally in Python to generate speech with laughter and sighs.

39.3kLinuxmacOSWindows2y ago

MITText-to-Speech & Voice Cloning

Sherpa ONNX

Sherpa ONNX is an offline speech processing engine replacing cloud voice APIs with local text-to-speech and recognition across mobile and edge hardware.

15.7kLinuxmacOSWindows5d ago

Apache-2.0Text-to-Speech & Voice Cloning

Tortoise TTS

Self-hosted text-to-speech engine and ElevenLabs alternative that generates realistic voice clones locally using autoregressive and diffusion models.

14.9kLinuxmacOSWindows2y ago

Apache-2.0Text-to-Speech & Voice Cloning

eSpeak NG

Compact open-source speech synthesizer replacing Speechify with lightweight, offline command-line text-to-speech for over 100 languages.

7.0kLinuxmacOSWindows1mo ago

GPL-3.0Text-to-Speech & Voice Cloning

Mycroft Mimic 3

Mycroft Mimic 3 is an open-source, offline neural text-to-speech engine replacing cloud services with local, private synthesis on Linux, Mac, and Docker.

1.3kLinuxmacOSWindows2y ago

AGPL-3.0Text-to-Speech & Voice Cloning