
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 in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
980
±0 (Oct 13〜)
Last commit
Apr 2026
Created on GitHub
Oct 29, 2025
Listed
—
Listed since the page was created
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | — |
| May 2026 | — |
| Jun 2026 | — |
| Jul 2026 | — |
| Aug 2026 | — |
| Sep 2026 | 979 |
| Oct 2026 | 980 |
| Nov 2026 | 980 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
T5Gemma-TTSAratako312Multilingual TTS model with voice cloning and duration control, based on T5Gemma encoder-decoder LLM.
GPT-SoVITSRVC-Boss62k1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
barksuno-ai39k🔊 Text-Prompted Generative Audio Model.
VoxCPMOpenBMB38kVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.
OpenVoicemyshell-ai38kInstant voice cloning by MIT and MyShell. Audio foundation model.
fish-speechfishaudio33kSOTA Open Source TTS.
Resources in similar research fields
sarashina2.2-ttssbintuitions90Sarashina2.2-TTS is a Japanese-centric text-to-speech system built on a large language model, developed by SB Intuitions.GitHubShared: Speech synthesis・Large language models
Emoji-TTSiron-mukakin52A fork of Irodori-TTS. It includes tools for generating captions (such as with LLM-Studio) and merging models. The inference capabilities have also been enhanced with features like continuous generation and voice quality adjustment.GitHubShared: Speech synthesis・Large language models- spoken-magpie-jaAtotti648Japanese instruction‑tuning dataset for the Spoken‑magpie LLM, built with CosyVoice2 TTS on 10 NVIDIA H200 GPUs, featuring diverse speaker voices and audio responses for prompts under 500 characters, with 50 sample entries publicly available.HF datasetShared: Speech synthesis・Large language models
- japanese-gpt-neox-smallrinna656kA 12‑layer, 768‑hidden Japanese GPT‑NeoX model trained on CC‑100, C4, and Wikipedia, compatible with Huggingface, with an optional toy prefix‑tuning weight that forces each sentence to end with a smiling‑face emoji.HF modelShared: Large language models
- Spark-X2.5-4B-Heretic-jp-ggufsoyaakinohara589kJapanese‑adapted Spark‑X2.5‑4B model (Heretic JP) with refusal attenuation, pretraining, instruction tuning and tool‑calling repair, available in GGUF quantizations from BF16 to Q4_K_M (~2.5 GiB), usable via llama.cpp for 1,048,576‑token context.HF modelShared: Large language models
chatterboxresemble-ai27kSoTA open-source TTS.Shared: Speech synthesis