whatmodel.sh / tts / Sonic 3.5

Sonic 3.5

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

Sonic 3.5 is a closed-weights text-to-speech model from Cartesia, released May 2026. Licence: proprietary.

Catalogue identity notes

Cartesia API model sonic-3.5 (RW-Voice-EQ Appendix Table 4, release 2026-06-16; ZONOS2 cites 'Cartesia Sonic 3.5'). Distinct from Sonic 3.6 (cartesia-sonic-3-6) and earlier Sonic versions.

Model information sources

Release date ↗

62.8±1.7comparison only: no current run option verifiedfrom 9 benchmark results across 4 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 Sonic 3.5, out of 148 with a score, then more from Cartesia.

#modelscorewhereRAMreleased
33MOSS-TTS v1.5 (8B) OpenMOSS63±2local~24GB2026-05
34GLM-TTS Z.ai63±2local~8.9GB2025-12
35Sonic 3.5 Cartesia63±2comparison only2026-05
36MiniMax Speech-02-HD MiniMax63±3api $100.00/M chars2025-03
37Fish Audio S2 Pro Fish Audio63±1api $15.00/M chars +local~11GB2026-03
more from Cartesia
57Sonic 3 Cartesia58±2api $65.00/M chars2025-10
59Sonic 2 Cartesia58±3comparison only2025-03
105Sonic (1) Cartesia42±3comparison only2024-05

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

$ what it's good at

other tests9 not in a task · 99% of its score
testresultvs the others in its rundifficultycountswhy
Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot1198.8 ✎▁···▁▃··█▄▁▇ beats 9/18avg 1078▇▇▇▇▇▇▇▇▇▇▇ 28%typical
Vapi Humanness · historical Elo, 2026-06-101257.2 ✎▃·▃▃▃·▃██▃·▃ beats 11/12avg 1080▇▇▇▇▇▇ 15%typical
ZTTS1-Eval in-the-wild · 10-language mean WER2.6% ✎▄·····█··▄██ beats 4/7avg 8.3%▇▇▇▇▇ 13%typical
ZTTS1-Eval Clean (FLEURS-R) · 9-language mean WER3.6% ✎▄·····▄█▄█·▄ beats 6/7avg 12%▇▇▇▇ 11%typical
ZTTS1-Eval in-the-wild · 10-language mean MSR-UTMOS2.77 / 5 ✎█··▄█▄····▄▄ beats 3/7hard · avg 2.00 / 5▇▇▇▇ 11%at its level
ZTTS1-Eval Clean (FLEURS-R) · 9-language mean MSR-UTMOS3.18 / 5 ✎▃▃█···▃···▃▃ beats 2/7medium · avg 2.52 / 5▇▇▇▇ 9.4%at its level
RW-Voice-EQ TTS · Acoustic Quality (human)3.37 / 5 ✎█·█········▄ beats 4/4medium · avg 2.70 / 5▇▇▇ 7.7%at its level
RW-Voice-EQ TTS · Voice Identity (human)3.53 / 5 ✎█·····▄····█ beats 4/4medium · avg 3.08 / 5▇▇ 4.4%at its level
1 more test
testresultvs the others in its rundifficultycountswhy
RW-Voice-EQ TTS · Long-Form Stability (human)3.53 / 5 ✎█······█·███ beats 3/4medium · avg 3.42 / 5▇ 0.6%blunt · at its level

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · ZONOS2 Technical Report (ZTTS… 44%, The Humanness Index by Vapi ·… 28%, The Humanness Index by Vapi ·… 15% and 1 more

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
ZONOS2 Technical Report (ZTTS1-Eval results)4▇▇▇▇▇▇▇▇▇▇▇▇▇ 44%CC BY-SA 4.0
The Humanness Index by Vapi · September 2026 public standings1▇▇▇▇▇▇▇▇ 28%CC BY 4.0
The Humanness Index by Vapi · June 2026 production export1▇▇▇▇ 15%CC BY 4.0
RW-Voice-EQ Bench (Hume AI)3▇▇▇▇ 13%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 62.8

$ 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