Local ASR model

Kyutai STT 2.6B English

Q: Can Kyutai STT 2.6B English run locally?

Kyutai STT 2.6B English is listed by LocalClaw as a local ASR option. Hardware fit depends on runtime, model size and backend support.

Catalogue summary: Kyutai's English-only 2.6B streaming ASR model. The decoder-only Transformer consumes Mimi audio tokens, uses a documented 2.5-second delay and emits punctuated transcripts with recoverable token timestamps.

Repository editorial metadata; verify comparative claims in the linked upstream material.

GPU recommendedspeech-to-text transcription1 languagesCC-BY-4.0

Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models

Open model filesRecommended verified starting point Open in UnslothLaunches Unsloth Desktop on this model Open Python packageVerified package page without exposing a command Open on Hugging FaceFiles, licence and model card Check my machineOptional: verify the fit with your saved hardware

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Catalogue quality

9.4/10

Catalogue speed

9.5/10

Model size

5.62 GB

Voices

N/A (ASR: outputs text + timestamps)

Can Kyutai STT 2.6B English run locally?

Kyutai STT 2.6B English can run locally for offline speech-to-text. Use the verified setup options on this page; no terminal command is required to choose the right path.

CC-BY-4.0 license. Review upstream restrictions before commercial use.

Upstream source

streaming

Audio profile

Cat. quality

9.4

Cat. speed

9.5

Audio

9.4

Best fit

Kyutai STT 2.6B English is best for offline transcription, speech indexing and local voice pipelines.

Hardware: gpucpuapple

Model details

Type

Local ASR model

Family

kyutai

Latency

medium

Formats

pytorchsafetensors

Languages

Context

Delay-streaming transformer, 2.5-second delay, English only

Install locally

Check runtimeConfirm the backend supports pytorch, safetensors on your machine.

Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.

Test locallyRun a short private audio prompt before moving into production workflows.

Good for

speech-to-text transcription
GPU recommended local workflows
streaming

Watch before shipping

Validate pronunciation, latency and artifacts with your own voice samples.
Review the upstream license and acceptable-use notes.
Benchmark on your target CPU, Apple Silicon or GPU setup.

Related TTS and speech models

CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw