← back

category

Text to speech

Generate speech from text, with voice cloning on some models, on your own hardware.

Side by side

Text to speech
ToolStarsLicenceTermsSelf-hostedLanguageLatestLast push
GPT-SoVITS62kMITOpen sourceYesPython20250606v2pro2026-10-06
Fish Speech33kOtherSource availableYesPythonv1.5.12026-10-05
Chatterbox27kMITOpen sourceYesPythonv0.1.22026-07-21
IndexTTS24kOtherSource availableYesPythonv2.5.02026-09-29
CosyVoice24kApache-2.0Open sourceYesPythonv2.02026-05-25
ebook2audiobook20kApache-2.0Open sourceYesPythonv26.10.12026-10-06
F5-TTS15kMITOpen sourceYesPython1.1.222026-09-21
Piper5.8kGPL-3.0Open sourceYesC++v1.8.02026-09-28
Kokoro-FastAPI5.5kApache-2.0Open sourceYesPythonv0.9.02026-10-05

9 tools

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Language
Python
Licence
MIT
Stars
62k
Latest
20250606v2pro
Last push
2026-10-06
IndexTTS

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

Language
Python
Licence
Other
Stars
24k
Latest
v2.5.0
Last push
2026-09-29
CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Language
Python
Licence
Apache-2.0
Stars
24k
Latest
v2.0
Last push
2026-05-25
F5-TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Language
Python
Licence
MIT
Stars
15k
Latest
1.1.22
Last push
2026-09-21
Piper

Fast and local neural text-to-speech engine

Language
C++
Licence
GPL-3.0
Stars
5.8k
Latest
v1.8.0
Last push
2026-09-28
Kokoro-FastAPI

Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, optional readalong web UI

Language
Python
Licence
Apache-2.0
Stars
5.5k
Latest
v0.9.0
Last push
2026-10-05

What these tools replace