LocalClaw/TTS/ARK-ASR-3B
Local ASR model

ARK-ASR-3B

Catalogue summary: 3B-scale multilingual ASR model built from a Whisper-style audio encoder, MLP adapter and Qwen decoder. Official code supports local Transformers inference and vLLM serving, with open Apache 2.0 safetensors for 19 languages.

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

GPU recommendedspeech-to-text transcription19 languagesApache 2.0
Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models
Open model filesRecommended verified starting pointOpen in UnslothLaunches Unsloth Desktop on this modelOpen official projectApplication source and guided setupOpen on Hugging FaceFiles, licence and model cardCheck 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
9.3/10
Catalogue speed
8.7/10
Model size
8.1 GB
Voices
N/A (ASR: outputs text)

Can ARK-ASR-3B run locally?

ARK-ASR-3B 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.

Apache 2.0 license. Still verify upstream usage notes before shipping.

Upstream source
multilinguallow-latency

Audio profile

Cat. quality
9.3
Cat. speed
8.7
Audio
9.1

Best fit

ARK-ASR-3B is best for offline transcription, speech indexing and local voice pipelines.

Hardware: gpuapple

Model details

Type
Local ASR model
Family
ark-asr
Latency
low
Formats
transformerssafetensorsvllmonnxmlx
Languages
zh, en, de, ja, fr, ko, es, pl, it, ro, hu, cs, nl, fi, hr, sk, sl, et, lt
Context
3B decoder-scale ASR, 8.1GB safetensors, 16 kHz audio, official Transformers and vLLM scripts

Install locally

01
Check runtimeConfirm the backend supports transformers, safetensors, vllm, onnx, mlx on your machine.
02
Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.
03
Test locallyRun a short private audio prompt before moving into production workflows.

Good for

  • speech-to-text transcription
  • GPU recommended local workflows
  • multilingual, low-latency

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

NVIDIA Parakeet TDT 0.6B v3 Local ASR model · Q 9.5 · Speed 9.7 NVIDIA Nemotron 3.5 ASR Streaming 0.6B Local ASR model · Q 9.4 · Speed 9.3 Alibaba Cloud (Qwen Team) Qwen3-ASR Local ASR model · Q 9.5 · Speed 9 Mistral AI Voxtral Mini 4B Realtime 2602 Local ASR model · Q 9.2 · Speed 9.4 OpenAI Whisper v3 Turbo Local ASR model · Q 9.1 · Speed 9.5 Audar AI Labs Audar-ASR-V1-Flash Local ASR model · Q 9.1 · Speed 9.4 Audar AI Labs Audar-ASR-V1-Turbo Local ASR model · Q 9.4 · Speed 8.6 NVIDIA Parakeet TDT 0.6B v2 Local ASR model · Q 9.4 · Speed 10
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw