Cartesia vs Murf AI
Listeners rate Cartesia's Sonic 3.6 above every Murf AI model.
ServiceNow, Decagon, and Quora run their production voice agents on Cartesia. One model, 44 languages, and voice cloning on the public API.
Voice quality
Listeners rate Sonic 3.6 above every Murf model
- 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 Falcon 2, Murf's highest-rated model, by more than 120 points.
Provider Voice Arena Elo
Higher is better
Accuracy
Sonic 3.6 makes fewer word errors than Falcon 2
- 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 Falcon 2, the difference between a confirmation number that lands and one the caller has to ask about.
Word error rate
Lower is better
Consistency
Sonic 3.6 holds a tighter latency spread than Falcon 2
- Coval times every request to first audio. The spread is the band the middle half of those requests fall inside.
- Sonic 3.6's band is half as wide as Falcon 2's, so response time stays steady from one call to the next.
Latency spread
Interquartile range of time to first audio; lower is better
Reasons why companies choose Cartesia over Murf AI
Human-like naturalness
Intonation, pacing, pronunciation, emotion, and audio quality that drive higher completion rates
Cartesia1276 EloMurf AI1155 EloFalcon 2982 EloSpeech Gen 2September 2026
Accuracy
Whether names, numbers, and terms come through as written.
Cartesia1.85% word error rateMurf AI2.22% word error rateFalcon 2September 2026
Consistency
At scale, the spread in latency matters more than the average.
CartesiaMiddle half of calls within a 72ms bandMurf AIMiddle half of calls within a 153ms bandFalcon 2September 2026
Languages
Comprehension and trust across a global customer base.
Cartesia44 languages from one model, with native accentsMurf AI35+ languages on Falcon 2Custom voices
How much audio it takes, and who is allowed to use one.
CartesiaInstant clone from 10 seconds, professional clone from 30 minutes, on the public APIMurf AIInstant cloning on the Enterprise plan only, and only for Falcon 2
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 Murf models on the board, Falcon 2 and Speech Gen 2.
How accurately does Cartesia read names and numbers?
Sonic 3.6 has a 1.85% word error rate in Coval's independent testing, against 2.22% for Murf Falcon 2. Coval transcribes each generated clip and compares it with the script, so fewer errors means more of the script is spoken as written.
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. Murf lists 35+ languages for Falcon 2.
Can I use my own voice with Cartesia?
Yes. An instant clone takes 10 seconds of audio and a professional clone takes 30 minutes. Both are self-serve on the public API. Murf offers instant cloning on its Enterprise plan only, and those clones work only with Falcon 2.
How long does it take to switch from Murf AI?
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.
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.