1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Sprache
- Python
- Lizenz
- MIT
- Sterne
- 62k
- Neuestes Release
- 20250606v2pro
- Letzter Push
- 2026-10-06
Generate speech from text, with voice cloning on some models, on your own hardware.
Änderungen in dieser Kategorie (RSS)
| Tool | Sterne | Lizenz | Bedingungen | Selbst hostbar | Sprache | Neuestes Release | Letzter Push |
|---|---|---|---|---|---|---|---|
| GPT-SoVITS | 62k | MIT | Open Source | Ja | Python | 20250606v2pro | 2026-10-06 |
| Fish Speech | 33k | Other | Quelltext verfügbar | Ja | Python | v1.5.1 | 2026-10-05 |
| Chatterbox | 27k | MIT | Open Source | Ja | Python | v0.1.2 | 2026-07-21 |
| IndexTTS | 24k | Other | Quelltext verfügbar | Ja | Python | v2.5.0 | 2026-09-29 |
| CosyVoice | 24k | Apache-2.0 | Open Source | Ja | Python | v2.0 | 2026-05-25 |
| ebook2audiobook | 20k | Apache-2.0 | Open Source | Ja | Python | v26.10.1 | 2026-10-06 |
| F5-TTS | 15k | MIT | Open Source | Ja | Python | 1.1.22 | 2026-09-21 |
| Piper | 5.8k | GPL-3.0 | Open Source | Ja | C++ | v1.8.0 | 2026-09-28 |
| Kokoro-FastAPI | 5.5k | Apache-2.0 | Open Source | Ja | Python | v0.9.0 | 2026-10-05 |
9 Tools
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
SOTA Open Source TTS
SoTA open-source TTS
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Generate audiobooks from e-books, voice cloning & 1158+ languages!
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Fast and local neural text-to-speech engine
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