Step-Audio-EditX
by stepfun-ai (organization)
A powerful 3B-parameter, LLM-based Reinforcement Learning audio edit model excels at editing emotion, speaking style, and paralinguistics, and features robust zero-shot text-to-speech (description from the project’s GitHub page)
Repository facts
- Stars
- 986
- Forks
- 80
- Open issues and pull requests
- 39
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- stepfun-ai · Organization
- Created
- Oct 29, 2025
- Last push
- Apr 9, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 340: index-tts/index-tts
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
24,559 starsPythonOther licenseLast push Sep 29, 2026
Rank 6,839: netease-youdao/Confucius4-TTS
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
842 starsPythonOther licenseLast push Sep 3, 2026
Rank 5,276: diodiogod/TTS-Audio-Suite
A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, In…
1,237 starsPythonOther licenseLast push Oct 17, 2026
Rank 346: QwenAudio/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
24,027 starsPythonApache-2.0Last push May 25, 2026
Rank 178: myshell-ai/OpenVoice
Instant voice cloning by MIT and MyShell. Audio foundation model.
37,925 starsPythonMITLast push Apr 19, 2025
Rank 1,900: metavoiceio/metavoice-src
Foundational model for human-like, expressive TTS
4,207 starsPythonApache-2.0Last push Jul 30, 2024