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

Granite Speech 4.1 2B

Compact Apache 2.0 speech-language model for multilingual ASR and bidirectional speech translation. Adds punctuation, truecasing, keyword biasing and Japanese ASR improvements.

GPU recommended speech-to-text transcription 6 languages Apache 2.0
Compare TTS models Open source page
Quality
9.2/10
Speed
8/10
Model size
4 GB
Voices
N/A (ASR/AST: outputs text or translation)

Can Granite Speech 4.1 2B run locally?

Granite Speech 4.1 2B can run locally for offline speech-to-text. Start with pip install transformers torchaudio soundfile.

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

pip install transformers torchaudio soundfile Upstream source
streamingrealtimemultilingual

Audio profile

Quality
9.2
Speed
8
Local
8.6

Best fit

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

Hardware: gpuapple

Model details

Type
Local ASR model
Family
granite-speech
Latency
low
Formats
pytorchsafetensors
Languages
en, fr, de, es, pt, ja
Context
2B speech-language model for ASR, AST, punctuation, truecasing and keyword-biased recognition

Install locally

01
Check runtimeConfirm the backend supports pytorch, safetensors on your machine.
02
Install modelUse the upstream command or repository instructions.
03
Test locallyRun a short private audio prompt before moving into production workflows.
pip install transformers torchaudio soundfile

Good for

  • speech-to-text transcription
  • GPU recommended 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

Kyutai Kyutai STT 2.6B Local ASR model · Q 9.4 · Speed 9.5 Alibaba Cloud (Qwen Team) Qwen3-ASR Local ASR model · Q 9.5 · Speed 9 OpenAI Whisper v3 Turbo Local ASR model · Q 9.1 · Speed 9.5 NVIDIA Canary 1B v2 Local ASR model · Q 9.3 · Speed 9 Microsoft Research VibeVoice ASR Local ASR model · Q 9.3 · Speed 7.5 Cohere Cohere Transcribe 03-2026 Local ASR model · Q 9 · Speed 8 NVIDIA Parakeet TDT 0.6B v2 Local ASR model · Q 9.4 · Speed 10 hexgrad Kokoro TTS Local TTS model · Q 9.2 · Speed 9.8
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw