LocalClaw/TTS/Audar-ASR-V1-Flash
Local ASR model

Audar-ASR-V1-Flash

Catalogue summary: Edge-tier Arabic-first generative ASR model from Audar AI Labs. It keeps the same dialect-aware transcription focus as Turbo in a 0.78B checkpoint, with downloadable BF16 safetensors, GGUF decoder variants, a required BF16 audio projector, Transformers, vLLM and llama.cpp paths, plus streaming notes for stable real-time captions.

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

Edge readyspeech-to-text transcription30 languagesAudarAI Open License v1.0
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 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
9.1/10
Catalogue speed
9.4/10
Model size
0.78B params; ~1.6 GB BF16 or 0.78-1.02 GB GGUF + mmproj
Voices
N/A (ASR: Arabic-first real-time transcription)

Can Audar-ASR-V1-Flash run locally?

Audar-ASR-V1-Flash 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.

AudarAI Open License v1.0 license. Review upstream restrictions before commercial use.

Upstream source
streamingrealtimemultilinguallow-latency

Audio profile

Cat. quality
9.1
Cat. speed
9.4
Audio
9.2

Best fit

Audar-ASR-V1-Flash is best for offline transcription, speech indexing and local voice pipelines.

Hardware: cpugpuedge

Model details

Type
Local ASR model
Family
audar
Latency
ultra-low
Formats
transformerssafetensorsggufvllmllama.cpp
Languages
ar, en, multilingual
Context
782M BF16 Qwen3-ASR adaptation, 30 s 16 kHz audio window, Arabic MSA/dialects plus English and 28 more languages; vLLM notes say BF16 fits 8 GB GPUs

Install locally

01
Check runtimeConfirm the backend supports transformers, safetensors, gguf, vllm, llama.cpp 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
  • Edge ready local workflows
  • streaming, realtime, multilingual

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

Audar AI Labs Audar-ASR-V1-Turbo Local ASR model · Q 9.4 · Speed 8.6 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 NVIDIA Parakeet TDT 0.6B v2 Local ASR model · Q 9.4 · Speed 10 NVIDIA Canary 1B v2 Local ASR model · Q 9.3 · Speed 9
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw