LocalClaw/TTS/Granite Speech 4.1 2B Plus
Local ASR model

Granite Speech 4.1 2B Plus

Catalogue summary: Official Apache 2.0 Granite Speech variant for rich local transcription. It keeps the 2B Granite speech-language architecture but adds speaker-attributed ASR, word-level timestamps, incremental decoding and keyword list biasing for English, French, German, Spanish and Portuguese.

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

GPU recommendedspeech-to-text transcription5 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 Python packageVerified package page without exposing a commandOpen 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
7.8/10
Model size
2B params; 4.22GB BF16 safetensors across three shards
Voices
N/A (rich ASR: outputs text with optional speaker labels and word timing)

Can Granite Speech 4.1 2B Plus run locally?

Granite Speech 4.1 2B Plus 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
multilingualdiarizationtimestampscontrollablelong-form

Audio profile

Cat. quality
9.3
Cat. speed
7.8
Audio
8.8

Best fit

Granite Speech 4.1 2B Plus is best for offline transcription, speech indexing and local voice pipelines.

Hardware: gpuapple

Model details

Type
Local ASR model
Family
granite-speech
Latency
medium
Formats
transformerspytorchsafetensorsvllm
Languages
en, fr, de, es, pt
Context
2B speech-language model, Apache 2.0, native Transformers support in transformers>=5.8, vLLM support from v0.23.0, speaker-attributed ASR and word-level timestamps on up to about 9 minute ASR/SAA segments

Install locally

01
Check runtimeConfirm the backend supports transformers, pytorch, safetensors, vllm 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, diarization, timestamps

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

IBM Granite Team Granite Speech 4.1 2B Local ASR model · Q 9.2 · Speed 8 IBM Granite Granite Speech 5.0 470M TurboCTC Local ASR model · Q 9.3 · Speed 9.8 OpenMOSS / MOSI.AI MOSS-Transcribe-Diarize 0.9B Local ASR model · Q 9.4 · Speed 8.4 OKESTRO AI Lab / Lee Junseok FastSLM-ASR Local ASR model · Q 9.2 · Speed 7.8 OpenMOSS / MOSI.AI MOSS-Audio 4B Instruct Local ASR model · Q 9.2 · Speed 7.7 FireRed Team FireRedAudio Local ASR model · Q 9.5 · Speed 6.6 ai-sage GigaChat Audio 10B A1.8B Local ASR model · Q 9.1 · Speed 6.7 KRAFTON AI A.X K2 Raon-Speech 21B-A3B Local ASR model · Q 9.4 · Speed 6.4
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw