fish-speech 开源项目推荐（42 个）

fishaudio /Bert-VITS2

带 multilingual-bert 的 vits2 主干网络

lenML /Speech-AI-Forge

🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

zeropointnine /tts-audiobook-tool

有声书制作应用支持过多的TTS模型（如Qwen3-TTS、OmniVoice、VibeVoice等），专注于高质量输出。还有音频同步阅读应用和独立服务器组件。

EvilFreelancer /docker-fish-speech-server

OpenAPI-like API-server for voice generation (TTS) based on fish-speech-1.5 model.

aivrar /LocalSoundsAPI

便携式离线 AI 音频工作室，带 Web UI 和本地 API——XTTS、Fish Speech、Kokoro、Stable Audio、ACE-Step、声音克隆、音乐生成（免安装）

Cvandia /nonebot-plugin-fishspeech-tts

适用于nonebot2的fish-speech和fish-audio的tts插件

aivrar /portable-tts-server

适用于 Windows 的便携式多 GPU 文本转语音服务器——10 个 AI 模型、网关 + 工作节点架构、7 阶段音频流水线、Whisper 验证、一键安装（无需系统 Python、无需 Docker、无需管理员权限）

reesertg /tuna-fish

RQ-Transformer（Fish Speech S2-Pro...）的最小化PyTorch实现推断<150条蟒蛇

DangNyan /fish-speech-pyqt6-gui

PyQt6 desktop GUI for Fish-Speech / OpenAudio TTS on Windows (no WSL)

licyk /Mizuoto

Open text-to-speech engines on one platform: CosyVoice, F5-TTS, GPT-SoVITS, OmniVoice, Qwen3-TTS, VoxCPM, Fish Speech and IndexTTS. They share one web UI, one command line and one HTTP API. Speak, clone and design voices, convert and edit speech, read whole books with a cast of voices, and fine-tune models on your own recordings.

Genesis1231 /fish-s2-rtx

Fish Audio OpenAudio S2-Pro on vLLM-Omni. low-latency ~100ms TTFA, OpenAI-compatible, runs on NVIDIA Blackwell (RTX 5090 / RTX PRO 6000). Self-hosted streaming TTS & voice cloning.

wine-fall /murmur

An always-on AI radio host for your terminal. It picks its own topics, talks, plays music, and keeps you company; type back and it answers in a voice that sounds human. Claude for a brain, fish-speech for a voice. MIT. TypeScript.

reezex0-ux /fish-s2-amd-hip

AMD/HIP compatibility fixes and GPU-side autoregressive optimizations for Fish Audio S2 Pro on GGML-based C++ runtimes.

Z3st105 /AIBLI

AI 虚拟角色音视频合成管线 — 从剧本到带字幕短视频的一站式自动化工具。支持 GPT-SoVITS / Fish Speech 双引擎热切换、多角色对话、OCR 智能内容生产链路。

5ekastanx /Voice-Synthesis

Проект для синтеза речи с использованием модели fish-speech/xtts. Позволяет преобразовывать текст в речи с клонированием голоса.

Edmon02 /armenian-video-dubbing

Open-source Armenian video dubbing pipeline with ASR, translation, voice cloning, lip-sync, and emotion-aware TTS

wangz-code /fish-tts

fish-speech文字转语音, 朗读tts还能克隆音色, 简单写了个前端,

andreaabcj-cmd /fish-audio-s2-pro-realtime-local-tts

Fish Audio S2 Pro as a real-time local TTS voice on a 16 GB GPU (RTX 5060 Ti, Windows) next to a 12B LLM: audio.cpp GGUF streaming build notes, benchmarks, samples, adapter, Ollama prompt-cache trick. EN + PT-BR.

ipfans /bob-plugin-fishaudio-tts

Fish Audio TTS for Bob Plugin is a tts plugin for bob. You can get a free API key from https://fish.audio/zh-CN/go-api/

xxrjun /local-inference

🐑 Run LLM inference locally for various downstream applications.