# Fish Speech Review

> Fish Speech review: Top-tier expressive multilingual open-weights TTS whose license moved from permissive to research/non-commercial; commercial use requires a.

![Fish Speech logo](https://www.versusref.com/logos/fish-speech.png)

Top-tier expressive multilingual open-weights TTS whose license moved from permissive to research/non-commercial; commercial use requires a license from Fish Audio or their hosted API.

Among the 46 text-to-speech tools we track, Fish Speech has the 6th-widest language coverage - a fit for multilingual and localization projects.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about Fish Speech

This is our verified profile of Fish Speech, a text-to-speech apis platform - top-tier expressive multilingual open-weights TTS whose license moved from permissive to research/non-commercial; commercial use requires a license from Fish Audio or their hosted API. Every fact about Fish Speech below carries the source it came from and the day we checked it.

Fish Speech does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Fish Speech quote, it is the fastest way for us to close that gap.

On capabilities, Fish Speech covers streaming audio output, instant voice cloning, emotion / style controls, and self-host / on-prem option. Each of those is verified against Fish Speech's own docs or dashboard, not marketing copy.

Fish Speech ranks the 6th-widest language coverage of the 46 text-to-speech tools we track, so where it lands for you depends on which of those matters more.

In total we track 12 verified facts for Fish Speech today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Fish Speech fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Streaming audio output | ✓  Yes | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |
| Instant voice cloning | ✓  Yes | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |
| Languages supported | 80 languages | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |
| Emotion / style controls | ✓  Yes | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |
| Model weights license | Fish Audio Research License (custom, non-commercial) | Jul 20 | [source](https://github.com/fishaudio/fish-speech/blob/main/LICENSE) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | PyTorch; vLLM (Omni) and SGLang serving; Docker | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | 4B (current flagship, S2 Pro per README | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |
| Hardware to self-host | GPU recommended (benchmarks on NVIDIA H200) | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |
| Hosted API available | Yes | Jul 20 | [source](https://fish.audio) |
| Project maintenance status | active | Jul 20 | [source](https://github.com/fishaudio/fish-speech/commits/main) |
| GitHub stars | 31,300 stars | Jul 20 | [source](https://github.com/fishaudio/fish-speech) |

## Fish Speech head-to-head

| Comparison | Record | Per use case |
| --- | --- | --- |
| [Fish Speech vs CosyVoice](https://www.versusref.com/tts/cosyvoice-vs-fish-speech/) | won 3 · lost 1 · tied 0 | Audiobooks: won; Dubbing: won; Self-Hosted: lost; Voice Agents: won |

Source: https://www.versusref.com/tts/tools/fish-speech/