/inference/kokoro

kokoro

Measured by one node on hardware we do not own, and signed by each of them. What machines here actually proved — never what the card claims.

matrix built 13 Oct 2026 · every field verified against the signature of the node that produced it, and re-verifiable by you: each signed figure carries the exact bytes the node signed (signing_payload_b64) and the signature over them, and the ed25519 public key is embedded in node_did. effective_ctx is the context length a node PROVED by recall, never the length a model card advertises
context declarednot declaredwhat the runtime reported. A node attests it was told this; nobody attests it is true.
context proved by recallnot probedthe largest size at which a machine could still find tokens planted across the whole prompt — start, middle and end, all of which had to come back.
Both numbers are needed to state a gap, and one of them is missing.

Languages, proved

English

Each question was put entirely in its own language and script, and the answer had to be right. A model with no coverage cannot parse the question, so answering in English is a failure here, not a pass. 1 proved of 4 asked — a language absent from the probe set was never asked, and is not a claim either way.

what it produced, measured

speech synthesis
produced3.8stook2.2sspeed1.7× faster than realtime

measured on Windows, 8 cores, 16 GB · realtime_factor 0.60 (wall ÷ media)

The fastest measurement any machine reported, signed by the machine that took it. Every other machine’s numbers are in the table below — a rate is a fact about a model and a computer, and two machines disagreeing is two hardware classes rather than one of them being wrong.

Capabilities, measured

Audiopassed
Given audio and asked to transcribe it.
Speech outpassed
The model itself turned text into audio — identified from the container bytes, not from what the engine labelled them, so an error page announced as audio cannot pass. Distinct from this gram running a separate text-to-speech engine: an operator choosing between them is choosing between two architectures.
signed by this network

What machines here proved

best throughput1.7× faster than realtime
machines that measured it1
regions it was proved in1
Every line traces to a node signature.
from the public record · unsigned

What the runtime says about it

No runtime metadata was attested for this model.The only unsigned block on this page. We attest we read these from the runtime — not that they are true. Nobody signs a model card.

Proven across regions

Bengaluru, Karnataka562114 · 1 node

The machine that measured it

nothing is averaged — the machine is what you are choosing
did:epn:002408…9e3c79Bengaluru · 562114 · speech-pod · 21 Sept 2026Intel64 Family 6 Model 151 Stepping 5, GenuineIntel · 15.7 GiB RAM
✓ Speech out · 1.7× faster than realtimeprobe 4ZqZx6NFGD…
✓ Speech out✓ Audio✓ 1 languages

Run this where your data already is

Tell us the workload, whose machines it should run on, and which jurisdiction it answers to.

Run a gramPut a machine on the network in this region; it signs its capacity into the room.Open a gramxStart your own room — an org, a community, a brand.Be invitedAccept a link from an admin to cross into the private room.