XTTS-v2 (17 languages, 6-second clone)
XTTS-v2 (17 languages, 6-second clone) · FP32 · by coqui
coqui/XTTS-v2
coqui · FP32 · on speech-hf · vendor build
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 3 Nov 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 advertisescontext 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.
what it produced, measured
speech synthesis
produced6.2stook33sspeed5.3× slower than realtime
measured on Linux, 12 cores, 53 GB · realtime_factor 5.34 (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
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.Audiopassed
Given audio and asked to transcribe it.signed by this networkEvery line traces to a node signature.
What machines here proved
best throughput5.3× slower than realtime
resident while loaded7.0 GiB · did:epn:002408…dae679
machines that measured it1
regions it was proved in1
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
Measured by
ranked on the provider standings
The machine that measured it
nothing is averaged — the machine is what you are choosingdid:epn:002408…dae679Singapore · 190464 · speech-hf · 3 Nov 2026Intel Xeon @ 2.20GHz · L4 22 GiB · 6 cores · 53.0 GiB RAM
✓ Speech out · 5.3× slower than realtimeprobe zXsbwQpUUK…
✓ Speech out✓ Audio
Run this where your data already is
Tell us the workload, whose machines it should run on, and which jurisdiction it answers to.