IBM Introduces Granite Speech 5.0 and Updates Turbo CTC and 4.1 2B Plus
Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
- Who
- IBM
- What
- released Granite Speech 5.0-2B and updated versions of Granite Speech 5.0-470M-TurboCTC and Granite Speech 4.1-2B-Plus
What happened
IBM introduced granite-speech-5.0-2b and updated granite-speech-5.0-470m-turboctc and granite-speech-4.1-2b-plus, all under Apache 2.0 with native Transformers support. The new 2B model improves transcription and translation with keyword lists up to 2,000 terms; Turbo CTC adds multilingual transcription and reaches 19,870 RTFx, about 1.6x its launch speed at the same accuracy level. The updated Plus model improves speaker attribution and timestamps, with long-form WER down 24%.
Why it matters
The comparison maps accuracy, throughput, and speaker attribution improvements to distinct recording workflows, offering a practical basis for choosing among the three models using their reported capabilities and evaluation results.
The story so far
IBM released granite-speech-5.0-2b and updated granite-speech-5.0-470m-turboctc and granite-speech-4.1-2b-plus, making all three available under Apache 2.0 with native Transformers support. The releases cover transcription and translation, faster multilingual transcription, and speaker attribution and timestamps. IBM said the new 2B model improves transcription and translation and supports keyword lists of up to 2,000 terms. For TurboCTC, IBM said the update adds multilingual transcription and reaches 19,870 RTFx, about 1.6 times its launch speed at the same accuracy level. IBM said the updated 4.1-2B-Plus improves speaker attribution and timestamps and reduces long-form word error rate by 24%.
Keep reading
Latest daily · Issue 28Mistral AI releases Voxtral 3 speech models and a voice agent SDKTrending now
- 1Mistral and NVIDIA Announce Industrial Engineering AI Collaboration and Open Benchmarks
- 2Mistral Releases Voxtral 3 Speech Models, Voice Agents API and LiveKit-Based SDK
- 3DeepSeek Open-Sources DeepInfer and API Components, With Model and Hardware Limits
- 4OpenAI Acquires Orchestra Bio to Add Drug Development Operations to Its Life Sciences Tools
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-21