whatmodel.sh / tts / Fish Speech 1.5

Fish Speech 1.5

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Fish Speech 1.5 is an open-weights text-to-speech model from Fish Audio, released December 2024. Licence: cc-by-nc-sa-4.0.

Catalogue identity notes

fishaudio/fish-speech-1.5 (model.pth + firefly-gan-vq-fsq-8x1024-21hz decoder). Predecessor of OpenAudio S1; distinct from Fish Speech 1.2/1.4 and from OpenAudio S1/S1-mini.

40.5±3.3#85 of 118 text-to-speech modelsfrom 4 benchmark results across 2 sources

Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.

$ how it compares

The text-to-speech models ranked either side of Fish Speech 1.5, out of 148 with a score, then more from Fish Audio.

#modelscorewhereRAMreleased
106Nabra-82M v0.1 oddadmix42±10local~0.3GB2026-07
107OpenAudio S1 Mini Fish Audio41±5api price unknown +local~1.7GB2025-06
108Fish Speech 1.5 Fish Audio41±3local~1.5GB2024-12
109EMA Lightning EMA Lightning (canberkkkkkk)40±3local~0GB2026-10
110Antalia-2 Mini Patientdesk.ai40±4comparison only2026-10
more from Fish Audio
5OpenAudio S1 Fish Audio71±8api $15.00/M chars2025-06
31Fish Audio S2.1 Pro Fish Audio63±3api $15.00/M chars2026-06
37Fish Audio S2 Pro Fish Audio63±1api $15.00/M chars +local~11GB2026-03

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests4 not in a task · 96% of its score
testresultvs the others in its rundifficultycountswhy
TTSDS2 listening test · speaker-similarity MOS (4 English domains)3.58 / 5 ✎▅·█▅▅·█▃▃▅·▅ beats 12/17easy · avg 4.03 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%at its level
TTSDS2 multilingual benchmark · Chinese overall (YouTube, 2025 round)80.6% ✎▄▄·····▄··▄█ beats 0/5very easy · avg 88%▇▇▇ 7.4%blunt
TTSDS2 listening test · naturalness MOS (4 English domains)3.24 / 5 ✎▅··▃▅··▅█▅██ beats 13/17medium · avg 3.30 / 5▇▇▇ 7.0%blunt · at its level
TTSDS2 multilingual benchmark · English overall (YouTube, 2025 round)86.8% ✎▂▂█·▂·█▆▂·▄▂ beats 11/17very easy · avg 89%▇▇ 4.9%blunt

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~1.47 GB · from github.com/fishaudio (official)
    git clone https://github.com/fishaudio/fish-speech && cd fish-speech && git checkout v1.5.0 && pip3 install torch==2.4.1 torchvision==0.19.1 torchaudio==2.4.1 && pip3 install -e .[stable] && huggingface-cli download fishaudio/fish-speech-1.5 --local-dir checkpoints/fish-speech-1.5 && python -m tools.run_webui --llama-checkpoint-path "checkpoints/fish-speech-1.5" --decoder-checkpoint-path "checkpoints/fish-speech-1.5/firefly-gan-vq-fsq-8x1024-21hz-generator.pth" --decoder-config-name firefly_gan_vq

Official weights and documentation: huggingface.co/fishaudio ↗

$ how the score was worked out · TTSDS2 listening test results… 83%, TTSDS2 multilingual benchmark… 12%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
TTSDS2 listening test results (ttsds/listening_test)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%MIT
TTSDS2 multilingual benchmark results (ttsds/leaderboard_data)2▇▇▇▇ 12%MIT
prior · pull toward the middle▇ 4%
weighted average= 40.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json