Fish Audio ORG

SOTA Open Source TTS

Fish Speech is an open-source text-to-speech system that converts written text into realistic spoken audio across 80+ languages, with fine-grained emotional control using inline tags like [whisper] or [excited] inserted directly into the text.

vits2 backbone with multilingual-bert

Bert-VITS2 is an abandoned Python text-to-speech system that combines VITS2 speech synthesis with a multilingual BERT model for more natural-sounding voices across languages. The team now recommends their newer Fish-Speech project instead.

An easy to understand TTS / SVS / SVC framework

Preprocess Audio for training

The official Python library for the Fish Audio API.

No description.

RTVC: Real-Time Voice Conversion GUI

OpenUTAU renderer for diffsinger / 适用于diffsinger的OpenUTAU渲染器，使用方法：https://github.com/xunmengshe/OpenUtau/wiki/%E4%BD%BF%E7%94%A8%E6%96%B9%E6%B3%95%EF%BC%88%E4%B8%AD%E6%96%87%EF%BC%89

No description.

A simple svs labeling tool

No description.

No description.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

Official documentation for products, services, and projects by Fish Audio

The official n8n node for the Fish Audio API.

The official Go SDK for the Fish Audio API.

No description.

⚡ A Simple / Speedy / Secure Link Shortener with Analytics, 100% run on Cloudflare.

Actix Web is a powerful, pragmatic, and extremely fast web framework for Rust.

Build cross-platform Native Progressive Web Apps for iOS, Android, and the Web ⚡️

No description.

An open framework and intermediary model for converters among project files of various singing voice synthesizers

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).

Hanabi interview demo