stepfun-ai / Step-Audio-EditXLinks
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
☆786Updated 2 weeks ago
Alternatives and similar repositories for Step-Audio-EditX
Users that are interested in Step-Audio-EditX are comparing it to the libraries listed below
Sorting:
- The official code repository for SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement☆699Updated 2 weeks ago
- ☆472Updated 7 months ago
- MiMo-Audio: Audio Language Models are Few-Shot Learners☆903Updated 3 months ago
- The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment☆1,018Updated last week
- GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning☆722Updated last week
- VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)☆870Updated 2 weeks ago
- ☆478Updated 7 months ago
- AudioStory: Generating Long-Form Narrative Audio with Large Language Models☆291Updated 3 months ago
- ☆425Updated 3 weeks ago
- Unofficial WIP LoRa Finetuning repository for VibeVoice☆290Updated 2 months ago
- Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation☆408Updated 3 weeks ago
- ☆336Updated 8 months ago
- ☆532Updated 2 months ago
- Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆1,114Updated this week
- [ICML 2025] SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation☆292Updated last month
- ☆289Updated 5 months ago
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆639Updated 8 months ago
- GLM-ASR-Nano: A robust, open-source speech recognition model with 1.5B parameters☆570Updated last week
- HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning☆1,020Updated 2 months ago
- Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation…☆1,270Updated 3 months ago
- Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching☆738Updated 3 weeks ago
- TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching☆807Updated 4 months ago
- ☆374Updated last month
- This is the official repo for the paper "LongCat-Flash-Omni Technical Report"☆444Updated last week
- High-quality Text-to-Audio Generation with Efficient Diffusion Transformer☆324Updated last week
- ☆1,593Updated this week
- VoiceStar: Robust, Duration-controllable TTS that can Extrapolate☆304Updated 6 months ago
- Fun-ASR is an end-to-end speech recognition large model launched by Tongyi Lab.☆338Updated last week
- KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution☆375Updated 4 months ago
- Di♪♪Rhythm 2: Efficient And High Fidelity Song Generation Via Block Flow Matching☆129Updated last month