LocalClaw/TTS/MOSS-Transcribe-Diarize 0.9B
Local ASR model

MOSS-Transcribe-Diarize 0.9B

Catalogue summary: End-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps and acoustic event awareness. Runs in one pass on recordings up to 90 minutes with hotword prompting and official Transformers, SGLang, vLLM and subtitle web app paths.

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

Apple Silicon readyspeech-to-text transcription50 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
9.4/10
Catalogue speed
8.4/10
Model size
1.8 GB
Voices
N/A (ASR + diarization: outputs speaker-aware text)

Can MOSS-Transcribe-Diarize 0.9B run locally?

MOSS-Transcribe-Diarize 0.9B 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
multilingualcontrollablelong-form

Audio profile

Cat. quality
9.4
Cat. speed
8.4
Audio
9.1

Best fit

MOSS-Transcribe-Diarize 0.9B is best for offline transcription, speech indexing and local voice pipelines.

Hardware: gpuapple

Model details

Type
Local ASR model
Family
moss
Latency
medium
Formats
transformerssafetensorsvllmsglang
Languages
multilingual
Context
0.9B model, 1.8GB safetensors, 50+ languages, 90-minute single-pass transcription

Install locally

01
Check runtimeConfirm the backend supports transformers, safetensors, vllm, sglang 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
  • Apple Silicon ready local workflows
  • multilingual, controllable, long-form

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

OpenMOSS / MOSI.AI MOSS-Audio 4B Instruct Local ASR model · Q 9.2 · Speed 7.7 OpenMOSS / MOSI.AI MOSS-TTS Local TTS model · Q 9.2 · Speed 6.8 OpenMOSS / MOSI.AI MOSS-TTS-Nano Local TTS model · Q 8.5 · Speed 9.7 FireRed Team FireRedAudio Local ASR model · Q 9.5 · Speed 6.6 KRAFTON AI A.X K2 Raon-Speech 21B-A3B Local ASR model · Q 9.4 · Speed 6.4 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
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw