whatmodel.sh / tts / Seed TTS 2.0 Standard

Seed TTS 2.0 Standard

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

Seed TTS 2.0 Standard is a closed-weights text-to-speech model from ByteDance Volcengine, released September 2025.

Catalogue identity notes

Source product model seed-tts-2.0-standard; voice configured default Chinese voice. June 2026 invocation. Do not map Azure Neural to Azure HD or Polly Neural to Polly Generative.

Model information sources

Release date ↗

84.0±5.2comparison only: no current run option verifiedfrom 1 benchmark result 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 Seed TTS 2.0 Standard, out of 148 with a score.

#modelscorewhereRAMreleased
1Seed TTS 2.0 Standard ByteDance Volcengine84±5comparison only2025-09
2Azure Neural TTS Xiaoxiao Microsoft Azure74±4comparison only
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

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

$ what it's good at

other tests1 not in a task · 89% of its score
testresultvs the others in its rundifficultycountswhy
CN-NewsTTS v0.1 · strict pronunciation accuracy87.9% ✎█··▄·█··▄··▄ beats 6/6hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · CN-NewsTTS Bench v0.1 89%

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
CN-NewsTTS Bench v0.11▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 89%CC BY 4.0
prior · pull toward the middle▇▇▇ 11%
weighted average= 84.0

$ 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