← kembali

kategori

Text to speech

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

Perbandingan berdampingan

Text to speech
AlatBintangLisensiKetentuanSelf-hostedBahasaTerbaruPush terakhir
GPT-SoVITS62kMITOpen sourceYaPython20250606v2pro2026-10-06
Fish Speech33kOtherSource availableYaPythonv1.5.12026-10-05
Chatterbox27kMITOpen sourceYaPythonv0.1.22026-07-21
IndexTTS24kOtherSource availableYaPythonv2.5.02026-09-29
CosyVoice24kApache-2.0Open sourceYaPythonv2.02026-05-25
ebook2audiobook20kApache-2.0Open sourceYaPythonv26.10.12026-10-06
F5-TTS15kMITOpen sourceYaPython1.1.222026-09-21
Piper5.8kGPL-3.0Open sourceYaC++v1.8.02026-09-28
Kokoro-FastAPI5.5kApache-2.0Open sourceYaPythonv0.9.02026-10-05

9 alat

GPT-SoVITS

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

Bahasa
Python
Lisensi
MIT
Bintang
62k
Terbaru
20250606v2pro
Push terakhir
2026-10-06
IndexTTS

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

Bahasa
Python
Lisensi
Other
Bintang
24k
Terbaru
v2.5.0
Push terakhir
2026-09-29
CosyVoice

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

Bahasa
Python
Lisensi
Apache-2.0
Bintang
24k
Terbaru
v2.0
Push terakhir
2026-05-25
F5-TTS

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

Bahasa
Python
Lisensi
MIT
Bintang
15k
Terbaru
1.1.22
Push terakhir
2026-09-21
Piper

Fast and local neural text-to-speech engine

Bahasa
C++
Lisensi
GPL-3.0
Bintang
5.8k
Terbaru
v1.8.0
Push terakhir
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

Bahasa
Python
Lisensi
Apache-2.0
Bintang
5.5k
Terbaru
v0.9.0
Push terakhir
2026-10-05

Apa yang digantikan alat-alat ini