# speech-to-text

4 related articles

Subscribe to updates

Hugging Face - Blog Oct 29, 2026
Models get patch releases too: Granite Switch 4.1.1 swaps adapters, not the base model, to ship new speech and decision skills
IBM's Granite Switch 4.1.1 arrives as a patch release, fully backwards compatible with 4.1 and requiring no migration. It updates a Granite Speech transcription model covering 10 languages with native punctuation and capitalization, and a Decision adapter in granitelib-core with improved overall performance on the Jev Decision Index test set. Apart from training those two new adapters, nothing was recomputed: the base model is untouched, and users compose the latest adapters and deploy.
IBM's Granite Switch 4.1.1 arrives as a patch release, fully backwards compatible with 4.1 and requiring no migration. It updates a Granite Speech transcription model covering 10 languages with native punctuation and capitalization, and a Decision adapter in granitelib-core with improved overall performance on the Jev Decision Index test set. Apart from training those two new adapters, nothing was recomputed: the base model is untouched, and users compose the latest adapters and deploy.
Granite Switch 4.1.1 speech-to-text
Fireworks AI Oct 23, 2026
Fireworks turns an hour of audio into text in under 4 seconds, serving Whisper v3-large on its own stack with alignment and translation
Fireworks released a beta speech-to-text API for the Whisper v3-large models, built around speed: on a dedicated endpoint, the asynchronous endpoint transcribes or translates one hour of audio in 4 seconds, about 900 times real time. Previously such services left users waiting seconds to minutes, and the gain here comes from serving-stack changes rather than a new model. On quality, whisper-v3-large reports a 2.00% word error rate for greedy inference on Librispeech Clean, matching the original open-source model; translation, word- and sentence-level timestamp alignment, audio preprocessing and voice activity detection ship in the same API.
Fireworks released a beta speech-to-text API for the Whisper v3-large models, built around speed: on a dedicated endpoint, the asynchronous endpoint transcribes or translates one hour of audio in 4 seconds, about 900 times real time. Previously such services left users waiting seconds to minutes, and the gain here comes from serving-stack changes rather than a new model. On quality, whisper-v3-large reports a 2.00% word error rate for greedy inference on Librispeech Clean, matching the original open-source model; translation, word- and sentence-level timestamp alignment, audio preprocessing and voice activity detection ship in the same API.
Fireworks Audio API Whisper v3-large speech-to-text
Mistral Blog Oct 20, 2026
Voxtral 3 folds listening, reasoning and speaking into one stream, finishing each voice turn in under a second
Mistral released Voxtral 3, which puts speech recognition, reasoning, tool calling and speech synthesis into a single real-time streaming pipeline, alongside a voice agent SDK. Previously, making an agent listen accurately, reason, speak naturally and act across systems in multiple steps remained difficult. Its Small transcription model beats Whisper, Scribe v2 and Gemini 3.5 Transcribe on multilingual transcription and diarization in English, French and Spanish, and realtime transcription runs below 500 ms latency.
Mistral released Voxtral 3, which puts speech recognition, reasoning, tool calling and speech synthesis into a single real-time streaming pipeline, alongside a voice agent SDK. Previously, making an agent listen accurately, reason, speak naturally and act across systems in multiple steps remained difficult. Its Small transcription model beats Whisper, Scribe v2 and Gemini 3.5 Transcribe on multilingual transcription and diarization in English, French and Spanish, and realtime transcription runs below 500 ms latency.
Voxtral 3 speech-to-text Text-to-Speech Voice agents Voice cloning
Hugging Face - Blog Oct 16, 2026
IBM Puts Chat, Decisions and Speech Behind One Endpoint: Three Adapters Share a KV Cache, VRAM Barely Moves
IBM released Granite Switch 4.1, which composes general decision-making, safety decision-making and speech transcription into a single hosted endpoint, with 8B and 30B versions occupying roughly the same GPU VRAM as the base model alone. The earlier Granite Switch project already allowed users to compose specialized adapters into custom models, while this release ships a Decision adapter, a Guardian safety adapter and Granite-Speech-5.0-Turbo-CTC precompiled into the model. Because the adapters are built as cache-efficient Activated LoRAs, the KV cache produced by a base-model generation can be reused for later adapter-based decisions, so switching between chat, decision and spoken requests does not rebuild the cache.
IBM released Granite Switch 4.1, which composes general decision-making, safety decision-making and speech transcription into a single hosted endpoint, with 8B and 30B versions occupying roughly the same GPU VRAM as the base model alone. The earlier Granite Switch project already allowed users to compose specialized adapters into custom models, while this release ships a Decision adapter, a Guardian safety adapter and Granite-Speech-5.0-Turbo-CTC precompiled into the model. Because the adapters are built as cache-efficient Activated LoRAs, the KV cache produced by a base-model generation can be reused for later adapter-based decisions, so switching between chat, decision and spoken requests does not rebuild the cache.
Granite Switch 4.1 Activated LoRA speech-to-text

You’re all caught up

Models get patch releases too: Granite Switch 4.1.1 swaps adapters, not the base model, to ship new speech and decision skills

Fireworks turns an hour of audio into text in under 4 seconds, serving Whisper v3-large on its own stack with alignment and translation

Voxtral 3 folds listening, reasoning and speaking into one stream, finishing each voice turn in under a second

IBM Puts Chat, Decisions and Speech Behind One Endpoint: Three Adapters Share a KV Cache, VRAM Barely Moves