whatmodel.sh / tts / Simba 3.2

Simba 3.2

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

Simba 3.2 is a closed-weights text-to-speech model from Speechify, released July 2026. Licence: proprietary.

66.8±3.2#8 of 118 text-to-speech modelsfrom 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 Simba 3.2, out of 148 with a score.

#modelscorewhereRAMreleased
11Grok TTS xAI68±3api $15.00/M chars2026-04
12FireRedTTS3 (base) FireRedTeam (Xiaohongshu)67±3local~12GB2026-08
13Simba 3.2 Speechify67±3api $6.00/M chars2026-07
14dots.tts Base (Pretrain) 2B dots.tts67±2comparison only2026-06
15MiniMax Speech 2.8 Turbo MiniMax66±3api $60.00/M chars2026-02

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

$ what it's good at

other tests1 not in a task · 96% of its score
testresultvs the others in its rundifficultycountswhy
Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot1279.2 ✎▁···▁▃··█▄▁▇ beats 17/18avg 1078▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%typical

$ where to run it

Through an API

api · $6.00/M chars · speechify.ai ↗ · price sourceUSD per 1M characters: SpeechifyAI lists usage after the included balance at $6 per 1M characters on Scale ($499/month; 'our lowest published rate'), $8 on Pro, $10 on Starter. Self-serve English uses Simba 3.2. Product: SpeechifyAI text-to-speech API. API model: Simba 3.2. Settings: Scale-plan rate. Price basis: published list rate. Exclusions: monthly plan fee; the page's third-party modelled estimates are not used. Currency: USD. Speechify official API pricing page, observed 2026-09-25.

$ how the score was worked out · The Humanness Index by Vapi ·… 96%

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
The Humanness Index by Vapi · September 2026 public standings1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%CC BY 4.0
prior · pull toward the middle▇ 4%
weighted average= 66.8

$ 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