stepfun-ai/
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
by stepfun-ai Python Apache-2.0 licence 80 forks Created Oct 2025 View on GitHub
- Stars
- 1,000
- 5% of stepfun-ai's stars
- Rank
- #66,472
- of 852,369 repos, top 8%
- In Python
- #12,076
- of 173,292 repos, top 7%
Among 852,369 repos
1k–1.6k stars: 23,672 repos, including Step-Audio-EditX
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #66,432
- Next milestone
- +6,205 stars to reach the top 1%
- Popular
- One of 66,533 repos with 1k+ stars
- Yearly average
- 963 stars a year since Oct 2025