flagship

Fish Speech 1.5

Apache-2.0 (v1.5 code) · CC-BY-NC-SA-4.0 (weights)

Earlier Fish Speech voice-cloning model; compare with S2 Pro

These recordings were generated with Fish Speech 1.5. Fish Audio S2 Pro is a separate release with different weights and licensing. Keep this page for comparing the original samples.

Looking for the newer release? See Fish Audio S2 Pro → These recordings remain labeled with their original version.

Hear Fish Speech 1.5

Fish Speech 1.5 · ttsds/fishspeech_1_5 · Same three scripts across the directory.

Run it yourself

Best for: Comparing earlier Fish Speech recordings with newer releases.

Noncommercial / separate license: Fish Speech 1.5 weights are CC-BY-NC-SA-4.0. Its v1.5.0 code tag is Apache-2.0; the current main branch has moved to S2 under a research license. Keep the checkpoint and code revision matched.

Code: Apache-2.0 (pinned v1.5.0 release). Weights: CC-BY-NC-SA-4.0 (Fish Speech 1.5). License sources checked 2026-09-20. Source 1 Source 2 Source 3 Source 4

Before you choose: Historical sample set. Check the exact 1.5 code and weight licenses; current repository instructions target S2 Pro.

Details awaiting a fresh review. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →

Qwen3-TTSListen side-by-side →Higgs Audio v2Listen side-by-side →ChatterboxListen side-by-side →

Choose an alternative to hear both models together.

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.”

Run Fish Speech 1.5

pip install fish-speech

Sources & setup details

Fish Speech 1.5 FAQ

Do I need a GPU to run Fish Speech 1.5?

The directory lists roughly 12 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

Can Fish Speech 1.5 clone voices?

Yes — Fish Speech 1.5 supports voice cloning from reference audio.

What license is Fish Speech 1.5 released under?

Fish Speech 1.5 is released under the Apache-2.0 (v1.5 code) · CC-BY-NC-SA-4.0 (weights) license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Fish Speech 1.5 support?

Fish Speech 1.5 supports English, Chinese, Japanese, Korean, French, German, Arabic, Spanish.

Is there a hosted Fish Speech 1.5 API?

OpenSpeech Cloud is accepting production-access interest for Fish Speech 1.5, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.