LLM Reference

Granite Speech 4.1 2B

Released
2026-04-29
Last refreshed
2026-04-29
Status
Researched 128d ago
Open sourceCommercial use: permittedMultimodalLong contextVision

Granite Speech 4.1 2B is a released long context and vision model with open-source and 128k context; evaluate it while provider pricing coverage matures.

Use it for

  • Teams evaluating long context and vision
  • Workloads that can use a 128k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Strict JSON or tool-calling flows
  • Teams that need a tracked hosted API route today
Specifications
Released
2026-04-29
Context
128k
Parameters
2B
Specialization
speech-recognition
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Created by

Creating reliable and adaptable AI solutions

Armonk, New York, United States
Founded 1945
Website
Pricing

No tracked provider token pricing is available yet.

About

IBM Granite Speech 4.1 2B is a multilingual ASR (Automatic Speech Recognition) and AST (Automatic Speech Translation) model trained on 174,000 hours of audio. ASR: English, French, German, Spanish, Portuguese, Japanese. Translation: X→English (French, German, Spanish, Portuguese, Japanese) and English→X (French, German, Spanish, Italian, Japanese, Mandarin Chinese). Features: punctuation/truecasing, keyword biasing, dual-head CTC encoder. Architecture: 16 conformer blocks + 2-layer window Q-former + Granite 4.0 1B LLM base (128K context). Variants: granite-speech-4.1-2b-plus (adds speaker-attributed ASR, word timestamps), granite-speech-4.1-2b-nar (non-autoregressive, higher throughput). Apache 2.0.

Top use-case fit

Long context

Included by capability and metadata signals in the decision map.

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

MultimodalAudio

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
LibriSpeech WER (test-clean)1.3test-cleanObserved 2026-04-30Source
Open ASR Leaderboard (average WER)5.3avg-11-datasetsObserved 2026-04-30Source

Migration checks

No linked migration route is available for this model yet.