A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

Voxtral Mini Realtime 2602

Transcribe speech into text with incremental output while processing audio.

Browser inferencePowered by WebAI · Private · Unlimited runs
About this model

Transcribe speech into text with incremental output while processing audio.

Created by
Mistral
License
Apache-2.0
Model released
Feb 4, 2026
Source repository created
Jan 21, 2026
Model weights · Q4F16
2.8 GB

Best for

  • Local captions and transcription of recordings in spoken languages supported by the checkpoint.

Keep in mind

  • Background noise, overlapping speakers, names and accents can reduce accuracy. Verify important transcripts.
  • Output contains transcription text. Speaker identity and word timestamps are unavailable in this adapter.
  • Samples cover English and Spanish. Other upstream languages are not quality-certified here.

Processed on your deviceInference runs in this browser. Input/output sharing requires consent for each run. Basic run logs include device information and approximate connection location. Model and runtime files download from external hosts. Saved downloads may be cleared by your browser.

Sources & technical details
Original model
https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602
Release verification
Verified
Release evidence
Publisher launch announcement names the open-weight realtime checkpoint.
Source updated
Mar 11, 2026
Browser model files
https://huggingface.co/onnx-community/Voxtral-Mini-4B-Realtime-2602-ONNX
Files updated
Mar 11, 2026
Artifact revision
db34633130c460bd650644fc18dc90710d9f3e38

Input

AUDIO

Sample result

Voxtral Mini Realtime 2602
Record a clip, then run inference. This does not send live audio to the model.

Output

Explore the tone of your audio

Choose a recording or try the sample to compare vocal emotion scores.

Benchmark evidence

Saved worker evidence is separate from benchmarks run on your device. It does not guarantee speed or quality on every browser.

Voxtral Mini Realtime 2602

3 configurations tested
Passed3
Failed0
TestedNov 14, 2026
Runtimetransformers.js 4.0.0-next.7

Quality criteria

No explicit quality gate recorded. Review per-case evidence; full certification is pending.

PrecisionDeviceResult
Q4F16GPU · WebGPUAcceleratedPassedModerate
Q4F16GPU · WebGPUAcceleratedPassedModerate
Q4F16GPU · WebGPUAcceleratedPassedModerate
Test setup & sample details
Quality gate
No explicit quality gate recorded. Review the per-case quality evidence; full certification is pending.
Tested
2026-11-14T20:50:30.416Z
Environment
Chrome module worker on Apple M3 Max
Runtime
transformers.js 4.0.0-next.7
Artifact revision
db34633130c460bd650644fc18dc90710d9f3e38
Fixture
{
  "file": "model-samples/voxtral-realtime/jfk.wav",
  "size": 352078,
  "sha256": "4d968ac99a1d0d4bc42ae8dd1552f4235e7b952a8121b39797f3dc2ca16123e9",
  "sha1": "069db705beb788608e93b99f1a4300451ebfb972",
  "url": "https://assets.localai.tools/samples/v1/files/4d968ac99a1d0d4bc42ae8dd1552f4235e7b952a8121b39797f3dc2ca16123e9/jfk.wav"
}
Rerun when
Artifact revision; Runtime version; Fixture checksum; Quality threshold
Per-case quality & failure details
[
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "wordErrorRate": 0,
      "reference": "And so my fellow Americans ask not what your country can do for you ask what you can do for your country."
    },
    "runtime": {
      "inferenceMs": 6795.099999964237,
      "audioSeconds": 11,
      "firstTokenMs": 1223.699999988079,
      "device": "webgpu",
      "precision": "q4f16",
      "version": "4.0.0-next.7",
      "loadMs": 3254.2000000476837,
      "totalMs": 10049.300000011921,
      "realTimeFactor": 0.6177363636331125,
      "grade": "fast",
      "artifactRevision": "db34633130c460bd650644fc18dc90710d9f3e38"
    }
  },
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "wordErrorRate": 0,
      "reference": "The morning train arrives at nine. Please bring your ticket."
    },
    "runtime": {
      "inferenceMs": 2319.900000035763,
      "audioSeconds": 4.5046875,
      "firstTokenMs": 364.19999998807907,
      "device": "webgpu",
      "precision": "q4f16",
      "version": "4.0.0-next.7",
      "loadMs": 3254.2000000476837,
      "totalMs": 5574.1000000834465,
      "realTimeFactor": 0.51499687825976,
      "grade": "fast",
      "artifactRevision": "db34633130c460bd650644fc18dc90710d9f3e38"
    }
  },
  {
    "precision": "q4f16",
    "device": "webgpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "wordErrorRate": 0,
      "reference": "El tren llega a las nueve. Por favor, trae tu billete."
    },
    "runtime": {
      "inferenceMs": 3006.5,
      "audioSeconds": 5.805,
      "firstTokenMs": 396.0999999642372,
      "device": "webgpu",
      "precision": "q4f16",
      "version": "4.0.0-next.7",
      "loadMs": 3254.2000000476837,
      "totalMs": 6260.700000047684,
      "realTimeFactor": 0.5179155900086133,
      "grade": "fast",
      "artifactRevision": "db34633130c460bd650644fc18dc90710d9f3e38"
    }
  }
]

Something not quite right?

Tell us what happened with Voxtral Mini Realtime 2602. Loading, results, or the page itself—we’re here for all of it.

Attachments Optional

Up to 3 files · 50 MB each

Browser, OS, CPU/GPU, memory, screen, storage, and network details are included automatically. Model inputs, results, and browsing history are not collected.