Main Page: Difference between revisions
Jump to navigation
Jump to search
Ttswikiadmin (talk | contribs) m (Protected "Main Page": High traffic page ([Edit=Allow only administrators] (indefinite) [Move=Allow only administrators] (indefinite))) |
Ttswikiadmin (talk | contribs) |
||
| (11 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
= Welcome to TTS Wiki = | |||
'''Note:''' This Wiki is still a work-in-progress. Contributions are welcome! | |||
'''TTS Wiki''' is a collaborative knowledge base dedicated to documenting and comparing latest '''Text-to-Speech (TTS)''' models and technologies. Our mission is to provide comprehensive, up-to-date information about the rapidly evolving landscape of speech synthesis. | |||
== Getting | == Getting Started == | ||
* [ | |||
* [ | === For Developers === | ||
* [ | * [[Installation Guides]] - Setup instructions for various TTS models | ||
* [[Installation Guides|Finetuning Guides]] - Walkthroughs for fine-tuning TTS models | |||
* | * [[Licensing Overview]] - Commercial usage rights and restrictions | ||
== Model Categories == | |||
=== Open Source Models === | |||
{| class="wikitable sortable" style="width: 100%;" | |||
! Model !! License !! Languages !! Voice Cloning !! Conversational | |||
!Fine-Tuning!! Date Released | |||
|- | |||
|[[VoxCPM]] | |||
|Apache-2.0 | |||
|English, Chinese | |||
|✅ | |||
|❌ | |||
|❌ | |||
|2025 | |||
|- | |||
|[[IndexTTS2]] | |||
|Custom (restrictive) | |||
|English | |||
|✅ | |||
|❌ | |||
|❌ | |||
|2025 | |||
|- | |||
| [[VibeVoice]] || MIT || English, Chinese || ✅ || ✅ | |||
|✅|| 2025 | |||
|- | |||
|[[Chatterbox]] | |||
|MIT | |||
|English | |||
|✅ | |||
|❌ | |||
|✅ | |||
|2025 | |||
|- | |||
|[[MegaTTS 3]] | |||
|MIT | |||
|English, Chinese | |||
|✅ | |||
|❌ | |||
|❌ | |||
|2025 | |||
|- | |||
|[[Orpheus TTS]] | |||
|Apache-2.0 | |||
|English | |||
|❌ | |||
|❌ | |||
|✅ | |||
|2025 | |||
|- | |||
|[[CSM-1B]] | |||
|Apache-2.0 | |||
|English | |||
|✅ | |||
|✅ | |||
|✅ | |||
|2025 | |||
|- | |||
|[[Kokoro-82M]] | |||
|Apache-2.0 | |||
|English | |||
|❌ | |||
|❌ | |||
|❌ | |||
|2025 | |||
|- | |||
|[[CosyVoice 2.0]] | |||
|Apache-2.0 | |||
|Chinese, English, Japanese, Korean | |||
|✅ | |||
|❌ | |||
|✅ | |||
|2024 | |||
|- | |||
| [[F5-TTS]] || MIT, CC-BY-NC || English, Chinese || ✅ || ❌ | |||
|✅|| 2024 | |||
|- | |||
| [[MaskGCT]] || MIT, CC-BY-NC || English, Chinese, Korean, Japanese, French, German || ✅ || ❌ | |||
|❌|| 2024 | |||
|- | |||
| [[StyleTTS 2]] || MIT || English || ✅ || ❌ | |||
|✅|| 2024 | |||
|- | |||
|[[XTTSv2]] | |||
|CPML (restrictive) | |||
|English, +16 | |||
|✅ | |||
|❌ | |||
|✅ | |||
|2023 | |||
|- | |||
|[[Tortoise TTS]] | |||
|Apache-2.0 | |||
|English | |||
|✅ | |||
|❌ | |||
|❌ | |||
|2022 | |||
|} | |||
=== Commercial Services === | |||
Coming soon | |||
== Contributing == | |||
Contributions are welcome! Here's how you can help: | |||
* '''Add new models''' - Document recently released TTS systems | |||
* '''Update comparisons''' - Share performance benchmarks and quality tests | |||
* '''Write tutorials and guides''' - Help others learn to use different TTS tools | |||
* '''Upload samples''' - Provide audio examples for model comparisons (please do not upload copyrighted content!) | |||
* '''Fix information''' - Correct outdated or inaccurate details | |||
'''Disclaimer:''' This wiki is maintained by the community and information may not always be current. Always verify details with official sources before making production decisions. Voice cloning should only be used with proper consent and for ethical purposes. | |||
[[Category:Main]] | |||
Latest revision as of 02:27, 22 September 2025
Welcome to TTS Wiki
Note: This Wiki is still a work-in-progress. Contributions are welcome!
TTS Wiki is a collaborative knowledge base dedicated to documenting and comparing latest Text-to-Speech (TTS) models and technologies. Our mission is to provide comprehensive, up-to-date information about the rapidly evolving landscape of speech synthesis.
Getting Started
For Developers
- Installation Guides - Setup instructions for various TTS models
- Finetuning Guides - Walkthroughs for fine-tuning TTS models
- Licensing Overview - Commercial usage rights and restrictions
Model Categories
Open Source Models
| Model | License | Languages | Voice Cloning | Conversational | Fine-Tuning | Date Released |
|---|---|---|---|---|---|---|
| VoxCPM | Apache-2.0 | English, Chinese | ✅ | ❌ | ❌ | 2025 |
| IndexTTS2 | Custom (restrictive) | English | ✅ | ❌ | ❌ | 2025 |
| VibeVoice | MIT | English, Chinese | ✅ | ✅ | ✅ | 2025 |
| Chatterbox | MIT | English | ✅ | ❌ | ✅ | 2025 |
| MegaTTS 3 | MIT | English, Chinese | ✅ | ❌ | ❌ | 2025 |
| Orpheus TTS | Apache-2.0 | English | ❌ | ❌ | ✅ | 2025 |
| CSM-1B | Apache-2.0 | English | ✅ | ✅ | ✅ | 2025 |
| Kokoro-82M | Apache-2.0 | English | ❌ | ❌ | ❌ | 2025 |
| CosyVoice 2.0 | Apache-2.0 | Chinese, English, Japanese, Korean | ✅ | ❌ | ✅ | 2024 |
| F5-TTS | MIT, CC-BY-NC | English, Chinese | ✅ | ❌ | ✅ | 2024 |
| MaskGCT | MIT, CC-BY-NC | English, Chinese, Korean, Japanese, French, German | ✅ | ❌ | ❌ | 2024 |
| StyleTTS 2 | MIT | English | ✅ | ❌ | ✅ | 2024 |
| XTTSv2 | CPML (restrictive) | English, +16 | ✅ | ❌ | ✅ | 2023 |
| Tortoise TTS | Apache-2.0 | English | ✅ | ❌ | ❌ | 2022 |
Commercial Services
Coming soon
Contributing
Contributions are welcome! Here's how you can help:
- Add new models - Document recently released TTS systems
- Update comparisons - Share performance benchmarks and quality tests
- Write tutorials and guides - Help others learn to use different TTS tools
- Upload samples - Provide audio examples for model comparisons (please do not upload copyrighted content!)
- Fix information - Correct outdated or inaccurate details
Disclaimer: This wiki is maintained by the community and information may not always be current. Always verify details with official sources before making production decisions. Voice cloning should only be used with proper consent and for ethical purposes.