ToolFish Audio/10 trustVerified

Fish Speech

Name: Fish Speech
Rating: 8

Expressive voice cloning and TTS — 33k stars under a research license.

About

Fish Speech is Fish Audio's text-to-speech and voice-cloning system (S2 Pro): expressive, multilingual synthesis with command-line, WebUI, server, and Docker inference — plus SGLang-Omni and vLLM-Omni serving recipes. 33k stars, paper-backed (arXiv 2603.08823). Licensing: the Fish Audio Research License — custom, NOT open source (the README warns 'we will take action against any violation'). Treat as source-available research code; commercial use needs a license from Fish Audio. Voice-cloning misuse risk is real — the project disclaims illegal use.

What it can do

**Expressive TTS**: S2 Pro with emotional range and multilingual voices
**Voice cloning**: clone voices from short reference audio
**Multiple interfaces**: CLI, WebUI, HTTP server, Docker
**Serving recipes**: SGLang-Omni and vLLM-Omni integrations
**Paper-backed**: technical report on arXiv

Setup

```bash

# see speech.fish.audio/install/ for the full guide

docker run -p 8000:8000 fishaudio/fish-speech

```

Command-line, WebUI, and server inference documented at speech.fish.audio. GPU recommended.

Prerequisites

NVIDIA GPU recommended. Review the Fish Audio Research License before any commercial use.

Use cases

TTSvoice cloningdubbingaccessibility

Works with

customGeneric API

Trust score — 8/10

/10 trustVerified

Scored 8/10 (verified tier, metrics-v1). Evidence: 33,013 GitHub stars (log-scaled vs catalog peers); last push 1d ago; 1 releases/12mo; 14 open issues. Manual review: expressive TTS/voice-cloning (S2 Pro), 33k stars, paper-backed, Docker/SGLang/vLLM serving; voice-cloning misuse risk. License: Fish Audio Research License — custom, NON-OSI ('we will take action against any violation'); describe as 'source-available', never 'open source'.

★ 33,013 GitHub stars

How the trust score is built

Full methodology →

Adoption · stars/downloads, log-scaled vs peers: 8.4/10
Maintenance · recency, releases, issue load: 8.2/10
Openness · license + docs: 5.8/10
Manual review · sanity read + red-flag check: 8.0/10

· 33,013 GitHub stars (log-scaled vs catalog peers)
· last push 1d ago; 1 releases/12mo; 14 open issues
· manual review: expressive TTS/voice-cloning (S2 Pro), 33k stars, paper-backed, Docker/SGLang/vLLM serving; voice-cloning misuse risk

Sources

Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.