vsref
Fish Speech logo

Fish Speech

OSS

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

Facts verified Jul 20, 2026Website →

What we know about Fish Speech

Fish Speech is 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. This profile tracks what we have verified about Fish Speech, each fact linked to a primary source and dated.

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.

In total we track 12 verified facts for Fish Speech today, and add coverage as the ingestion pass revisits it. Where a number is a vendor claim rather than our own measurement, it is labeled as such on the Fish Speech fact sheet below, and each row links the primary source it came from so you can check our work.

Whether Fish Speech is the right call depends on your use case more than any single spec, which is why the head-to-head verdicts below score it per scenario rather than crowning one overall winner. Use the fact sheet for the raw numbers, and the matchups for how Fish Speech actually fares against the platforms buyers most often weigh it against.

Fact sheet

Capabilities
Capabilities facts
Streaming audio output✓ YesJul 20
Instant voice cloning✓ YesJul 20
Languages supported80 languagesJul 20
Emotion / style controls✓ YesJul 20
Compliance & trust
Compliance & trust facts
Self-host / on-prem option✓ YesJul 20
Model weights licenseFish Audio Research License (custom, non-commercial)Jul 20
Build experience
Build experience facts
Official SDKsPyTorch; vLLM (Omni) and SGLang serving; DockerJul 20
Commercial
Commercial facts
Model size (parameters)4B (current flagship, S2 Pro per READMEJul 20
Hardware to self-hostGPU recommended (benchmarks on NVIDIA H200)Jul 20
Hosted API availableYesJul 20
Project maintenance statusactiveJul 20
GitHub stars31,300 starsJul 20

Considering a switch? Best Fish Speech alternatives →

Fish Speech head-to-head

Fish Speech vs CosyVoicewon 3 · lost 1 · tied 0
AudiobookswonDubbingwonSelf-HostedlostVoice Agentswon