speech recognition

NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable speech model that transcribes 40 languages, translates 31 to or from English and labels speakers in 13. It is available on Hugging Face and ModelScope alongside Granary v2 data and NeMo Speech fine-tuning recipes.

iFLYTEK detailed SparkAudio 1.0 at its 2026 Global 1024 Developer Festival. The speech foundation model combines a 0.65-billion-parameter audio encoder with a 30B-A3B mixture-of-experts language model, trained on 13 million hours of audio. iFLYTEK also launched Robot Super Brain Platform 3.0 for embodied robots.

IBM released granite-speech-5.0-2b, a 2B-parameter speech-language model trained on 390,000 hours of public audio. IBM claims it ranks #2 among open-weight ASR models with a 5.06% average English WER. IBM also updated its 470M Turbo CTC model to 19,870 RTFx and refreshed the weights of granite-speech-4.1-2b-plus.

Alibaba's Qwen team has released Qwen-Audio-3.1, a five-model lineup covering speech recognition, text-to-speech, and real-time voice interaction. Alongside the release, Alibaba cut API pricing by up to 95 percent for ASR, 85 percent for real-time models, and 70 percent for TTS.

Microsoft Research has released VibeVoice-ASR-Streaming-7B, an open-weight streaming automatic speech recognition model that transcribes both who is speaking and what they say in real time. The model, listed at 9B parameters despite its name, supports 10 languages and custom hotwords under an MIT license.

IBM has released two new 470M-parameter Granite Speech models that transcribe audio at over 12,600x real-time speed on an NVIDIA H200 GPU. The encoder-only models achieve 4.85-5.00% word error rate while running over 20x faster than prior Granite Speech versions.

OpenAI released GPT Transcribe and GPT Live Transcribe, improving word error rate to 3.31 percent and cutting prices 25 percent to $0.0045 per minute. Independent benchmarks still place OpenAI behind ElevenLabs, Google, and Mistral on transcription accuracy.