whatmodel.sh / tts / OpenAudio S1

OpenAudio S1

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

OpenAudio S1 is a closed-weights text-to-speech model from Fish Audio, released June 2025. Licence: proprietary.

71.3±7.5#2 of 118 text-to-speech modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

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 OpenAudio S1, out of 148 with a score, then more from Fish Audio.

#modelscorewhereRAMreleased
3Gemini 2.5 Flash Preview TTS Google72±3comparison only2025-05
4Voxtral TTS (4B) Mistral71±4api $16.00/M chars +local~10GB2026-03
5OpenAudio S1 Fish Audio71±8api $15.00/M chars2025-06
6Gemini 2.5 Pro Preview TTS Google69±3comparison only2025-05
7Qwen-Audio-3.0-TTS-Plus Alibaba69±2api $20.00/M chars2026-09
more from Fish Audio
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
88Fish Speech 1.2 Fish Audio49±14local~1.2GB2024-07

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

$ what it's good at

voice cloning▁·▁▁▁▁▁▁▇█▃▃ #3 of 37 * · 78% of its score · 2 tests

Trails dots.tts SOAR 2B, Qwen-Audio-3.0-TTS-Plus here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Seed-TTS test-en · Whisper large-v3 WER lab1.1% ✎▁···▂▂▂▂█▆▄▃ beats 34/35avg 3.6%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%blunt · small run
Seed-TTS test-zh · Paraformer CER lab0.5% ✎▁·▂▁▁▁▂▃▅█·▃ beats 29/30avg 2.1%▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%blunt · small run
other tests2 not in a task · 0.0% of its score
testresultvs the others in its rundifficultycountswhy
Long-TTS-Eval · Fish truncated English WER lab6.3% ✎█··········█ beats 0/1—not counted yet: no other model in the same run to compare it with
Long-TTS-Eval · Fish truncated Chinese CER lab6.4% ✎█··········█ beats 0/1—not counted yet: no other model in the same run to compare it with

$ where to run it

Through an API

api · $15.00/M chars · docs.fish.audio ↗ · price sourceFish Audio lists s1 at $15.00 per 1M UTF-8 bytes of input text. Stored as per 1M characters, which equals bytes only for ASCII (e.g. English) text; non-ASCII characters take 2-4 bytes, so per-character cost is higher for those scripts. Product: Fish Audio TTS API. API model: s1. Settings: pay-as-you-go. Price basis: published list rate (byte-billed). Exclusions: none stated. Currency: USD. Fish Audio official pricing docs, observed 2026-09-25.

$ how the score was worked out · Fish Audio S2 Technical Report 78%

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
Fish Audio S2 Technical Report · lab-reported2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 78%CC BY 4.0
prior · pull toward the middle▇▇▇▇▇▇▇ 22%
weighted average= 71.3

not counted (2)

Fish Audio S2 Technical ReportLong-TTS-Eval · Fish truncated English WER [correct]6.3%fewer than three models have this test yet, or this source ran it for this model alone
Fish Audio S2 Technical ReportLong-TTS-Eval · Fish truncated Chinese CER [correct]6.4%fewer than three models have this test yet, or this source ran it for this model alone

$ 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