whatmodel.sh / tts / TTS-1

TTS-1

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

TTS-1 is a closed-weights text-to-speech model from OpenAI, released November 2023. Licence: proprietary.

59.1±3.8#43 of 118 text-to-speech modelsfrom 3 benchmark results across 1 source

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 TTS-1, out of 148 with a score, then more from OpenAI.

#modelscorewhereRAMreleased
50E2 TTS Base (F5-TTS reproduction) SWivid (SJTU X-LANCE)60±2local~1.3GB2024-10
51MiniMax Speech-02-Turbo MiniMax60±3api $60.00/M chars2025-04
52TTS-1 OpenAI59±4api $15.00/M chars2023-11
53MaskGCT Amphion (CUHK-Shenzhen)59±1local~6.6GB2024-10
54MGM-Omni-TTS 2B (0927) MGM-Omni (CUHK)59±4comparison only2025-09
more from OpenAI
58GPT-4o mini TTS OpenAI58±2comparison only2025-03
61TTS-1 HD OpenAI57±7api $30.00/M chars2023-11

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

$ what it's good at

other tests3 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
RW-Voice-EQ TTS · Acoustic Quality (human)3.33 / 5 ✎█·█········▄ beats 0/4medium · avg 2.70 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%at its level
RW-Voice-EQ TTS · Acting / Role-Fit (human)3.16 / 5 ✎▄·····█····▄ beats 0/3medium · avg 2.58 / 5▇▇▇▇▇▇▇▇▇▇▇▇ 31%at its level
RW-Voice-EQ TTS · Voice Identity (human)3.46 / 5 ✎█·····▄····█ beats 1/4medium · avg 3.08 / 5▇▇▇▇▇▇▇▇▇ 23%at its level

$ where to run it

Through an API

api · $15.00/M chars · developers.openai.com ↗ · price sourceUSD per 1M input characters, direct character tariff; not derived from tokens. Product: Audio speech API. API model: tts-1. Settings: endpoint=/v1/audio/speech, tier=standard. Price basis: published rate. Currency: USD.

$ how the score was worked out · RW-Voice-EQ Bench (Hume AI) 94%

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
RW-Voice-EQ Bench (Hume AI)3▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%CC BY 4.0
prior · pull toward the middle▇▇ 6%
weighted average= 59.1

$ 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