Skip to main content
Radar

Keep up with the models you depend on. Follow price changes, retirements, and API updates.Follow the models you depend on.

Follow model changes
BenchLM

Zonos 2

CurrentReleased Jun 12, 2026Open WeightNon-ReasoningN/A contextZyphra model documentation

Released Jun 12, 2026 — see all recent releases

Decision reading
Zonos 2 is tracked, but not publicly ranked yet. The profile exposes 0 sourced benchmark rows and leaves unsupported fields blank until a published record exists.

Data as of September 10, 2026 · How the score is built

View Zyphra model evaluation resultsFind alternatives

Share or export

Share on XLinkedInSocial cardBenchmarks CSVJSON

Voice benchmark evidence

Zonos 2 model evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.

WER (F16 reference)
2.79
Speaker similarity
66.75
UTMOS
4.40
Provider snapshot · Zyphra · 2026-06-12
Open benchmark profileModel documentation

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
Not publishedZyphra model documentation
Context window
N/A
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not sourced yet
Availability
Released June 12, 2026 under Apache 2.0 as an 8B-total, 900M-active MoE (Zyphra/ZONOS2, with GGUF builds for the zonos2.cpp runtime) covering 34 languages across three tiers, and hosted free for a promotional period on Zyphra Cloud.
Cloud regions
Not tracked yet
Lifecycle
Current
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing recordZyphra model documentation
Self-host
Open weights available; hardware estimate not sourced
Rate limits
Not tracked yet

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.

Estimate VRAM from known parameters

Lineage

The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Jun 12, 2026 · you are here

    Zonos 2

    Not publicly ranked · Price not listed

Base entry

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

We track Zonos 2, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.

Zonos 2 is a open weight model with a N/A context window. No explicit reasoning mode is documented in this profile.

Released June 12, 2026 under Apache 2.0 as an 8B-total, 900M-active MoE (Zyphra/ZONOS2, with GGUF builds for the zonos2.cpp runtime) covering 34 languages across three tiers, and hosted free for a promotional period on Zyphra Cloud.

Zonos 2 is a display-only open-weight multilingual text-to-speech model with voice cloning. Voice results remain separate from BenchLM’s weighted text-model ranking.

The profile has no source-displayable benchmark row yet.

Radar

Zonos 2 release history

Full release history

Radar confirmed these at the source. Use Zonos 2 in your work? Explore Radar to follow supported changes and choose your alerts.

Frequently asked questions

How does Zonos 2 perform overall in AI benchmarks?

Zonos 2 does not have any source-displayable benchmark rows yet, so this profile does not assign a public score or rank. Documented specifications remain visible, while score-led charts and claims stay unavailable until a published evaluation can be attached to the exact model.

Is Zonos 2 open source?

Zonos 2 is an open-weight model from Zyphra. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Does Zonos 2 have full benchmark coverage on BenchLM?

No. Zonos 2 currently has 0 source-displayable rows across 434 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Zonos 2?

Zonos 2 has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.

Compare Zonos 2 with every tracked model482 comparisons

Last updated September 10, 2026. Runtime fields remain blank until a sourced snapshot exists.

Watch Zonos 2 in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 2,000+ readers.