Skip to content
New · the open voice benchmark is liveRead it
cantari
Engine

Zonos

Open-weight Zyphra engine with four accent voices.

Baseline rating with limited arena votes so far.

4 accentsOpen-source
Generated by Zonos
4 real voices · previews below
The numbers

Scores, speed, and the real rate.

The same trust rows as the open benchmark: a third-party quality score, our own measured latency, and the raw engine cost in the open.

Quality Elo*
1000*
Measured latency
4523ms measured 2026-06-10
Languages
1 language
Follows [cues]
Plain read, ignores cues
Engine cost
$7/M in · $0 out rate checked 2026-06-11

The provider’s published rate when we last checked. Rates move, and when they do we update this row. It’s here so you can weigh our flat pricing against the raw cost underneath, instead of taking our word for it.

Rights
Apache-2.0 model; commercial OK

* Quality Elo from the Artificial Analysis Speech Arena, retrieved June 10, 2026. It is a user-vote arena rating; the top model of all rated is Fun-Realtime-TTS at 1228.06. Zonos: Baseline rating with limited arena votes so far.

Latency is our own wall-clock time to full audio, measured 2026-06-10 on the same path that serves the studio. A measurement, not a server SLA.

Voices

Every voice Zonos ships.

Press play to hear each voice: real output from this engine, recorded unedited. What you hear is what it produced.

Quinn

Clear American female

Miles

Even American male

Imogen

Composed British female

Alfie

Mellow British male

Best for

Where Zonos earns its place.

American and British accent reads in English.

Hear it in the studio.

Open the studio and generate real audio through Zonos. No sign-up required to listen.