All models
flagship

Fish Speech

Apache-2.0

Open-source TTS that benchmarks above closed-source

Fish Speech (and its successor OpenAudio) is a multilingual TTS family with strong zero-shot voice cloning across a dozen-plus languages, no phoneme dependency, and consistently top rankings on open TTS leaderboards. The hosted version skips its fairly heavy local setup.

Voices

1 voice
Female
Reference clonedefault
american

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install fish-speech

Fish Speech FAQ

Do I need a GPU to run Fish Speech?

For practical speeds, yes — plan on roughly 12 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can Fish Speech clone voices?

Yes — Fish Speech supports voice cloning from reference audio.

What license is Fish Speech released under?

Fish Speech is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Fish Speech support?

Fish Speech supports English, Chinese, Japanese, Korean, French, German, Arabic, Spanish.

Is there a hosted Fish Speech API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to Fish Speech and every other model in this directory. No CUDA, Docker, or GPU needed.