Listeners rate Cartesia's Sonic 3.6 above Gradium TTS.
ServiceNow, Decagon, and Quora run their production voice agents on Cartesia. One model, 44 languages, first audio in under 90ms.
Voice quality
Listeners rate Sonic 3.6 above both Gradium TTS models
- Artificial Analysis plays listeners two clips of the same line without naming the model, and rates every model on the board the same way.
- Sonic 3.6 leads Gradium TTS (Sep 2026), Gradium's newest model, by more than 110 points.
Provider Voice Arena Elo
Higher is better
Accuracy
Sonic 3.6 makes fewer word errors than Gradium TTS
- Coval transcribes every clip each model generates and compares it with the script, so a lower rate means more of the script is spoken as written.
- Sonic 3.6 misreads fewer words than Gradium TTS, the difference between a confirmation number that lands and one the caller has to ask about.
Word error rate
Lower is better
Speed
Sonic 3.6 generates speech more than three times as fast as Gradium TTS (Aug 2026)
- Artificial Analysis times every model on the board with the same harness, in characters generated per second.
- Generating well ahead of playback keeps a long turn from stalling mid-sentence.
Characters per second
Higher is better
Reasons why companies choose Cartesia over Gradium
Human-like naturalness
Intonation, pacing, pronunciation, emotion, and audio quality that drive higher completion rates
Cartesia1291 EloGradium1175 EloGradium TTS (Sep 2026)1156 EloGradium TTS (Aug 2026)October 2026
Accuracy
Word error rate (WER) on the speech each model generates: whether names, numbers, and terms come through as written.
Cartesia1.89% WERGradium2.2% WERGradium TTS (Sep 2026)October 2026
Latency
Decides whether it feels like a conversation or a phone tree.
Cartesia<90ms to first audioGradium<300ms to first token when streaming, as Gradium publishes itLanguages
Comprehension and trust across a global customer base.
Cartesia44 languages from one model, with native accentsGradium5 languages: English, French, German, Spanish, and Portuguese
Frequently asked questions
How is the quality score measured?
It comes from Artificial Analysis, an independent benchmark. Listeners hear two clips of the same line without being told which model produced either, and pick the one they prefer. Sonic 3.6 rates above both Gradium models on the board, Gradium TTS (Sep 2026) and Gradium TTS (Aug 2026).
Does Cartesia make fewer word errors than Gradium?
Yes. Sonic 3.6 has a 1.89% word error rate in Coval's independent testing, against 2.2% for Gradium TTS. Coval transcribes each generated clip and compares it with the script, so the rate counts the words a caller would hear wrong.
How many languages does Cartesia support?
44 languages from one model, including English, Spanish, French, German, and Japanese. Accents are calibrated per region rather than bolted onto an English model. Gradium's documentation lists 5 languages for Gradium TTS.
How long does it take to switch from Gradium?
One to two weeks for most teams. Cartesia is integrated into the major voice agent platforms and every model is on the public API, so there is no platform to move onto and nothing to unpick later.
More comparisons
Get started today
Talk to an expert.
Connect with a member of our team and learn how Cartesia can help you build world-class voice experiences.
Start building.
Access our models via API and bring a voice agent into production in minutes.