whatmodel.sh / tts / Gradium TTS

Gradium TTS

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

Gradium TTS is a closed-weights text-to-speech model from Gradium, released December 2025. Licence: proprietary.

Catalogue identity notes

Vapi registry gradium-gradium-tts, apiModelId gradiumtts. Rating-only comparison identity; no price, API or run metadata asserted.

50.9±2.6#63 of 118 text-to-speech modelsfrom 2 benchmark results across 2 sources* 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 Gradium TTS, out of 148 with a score.

#modelscorewhereRAMreleased
76Spark-TTS 0.5B SparkAudio52±3local~2.9GB2025-02
77Llasa-8B HKUST Audio52±3local~20GB2025-01
78Gradium TTS Gradium51±3api $38.00/M chars2025-12
79OpenVoice V1 MyShell51±14local~0.3GB2024-01
80Eleven Multilingual v2 ElevenLabs51±5api $100.00/M chars2023-08

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

$ what it's good at

other tests2 not in a task · 97% of its score
testresultvs the others in its rundifficultycountswhy
Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot1089.8 ✎▁···▃▃··█▄▁▇ beats 1/18avg 1078▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%typical
Vapi Humanness · historical Elo, 2026-06-101098.6 ✎▃·▃▃▃·▃██▃·▃ beats 2/12avg 1080▇▇▇▇▇▇▇▇▇▇▇▇▇ 33%typical

$ where to run it

Through an API

api · $38.00/M chars · docs.gradium.ai ↗ · price sourceUSD per 1M characters: Gradium states Text-to-Speech uses 1 credit / character and sells additional credits at $3.8 per 100k on the L plan ($1,615/month; lowest published self-serve rate), $4.0 M, $5.0 S, $6.9 XS (x10). Gradium's TTS API has a single default model (model_name 'default'); credits are not model-specific. Product: Gradium text-to-speech API. API model: default Gradium TTS (Vapi id gradiumtts). Settings: L-plan usage-based rate. Price basis: vendor USD-per-credit rate x vendor-stated 1 credit per character. Exclusions: monthly plan fee, included credits, voice cloning. Currency: USD. Gradium official pricing page, observed 2026-09-25.

$ how the score was worked out · The Humanness Index by Vapi ·… 64%, The Humanness Index by Vapi ·… 33%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%CC BY 4.0
The Humanness Index by Vapi · June 2026 production export1▇▇▇▇▇▇▇▇▇▇ 33%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 50.9

$ 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