speech recognition

9 articles tagged with speech recognition

November 10, 2026
product updateGoogle

Google AI Edge Gallery adds on-device ASR and TTS, with ML Kit transcription across 100+ languages

Google introduced on-device Automatic Speech Recognition and Text-to-Speech in Google AI Edge Gallery on Nov. 10, 2026. ML Kit's ASR covers 100+ languages at 10x real-time speed, and its diffusion TTS begins speaking in about 100 ms. Cross-platform developers get open-weight speech bundles through MediaPipe Tasks and LiteRT.

November 6, 2026
benchmarkHugging Face

Open ASR Leaderboard adds private Egyptian and Nigerian English test sets from Liva AI

The Open ASR Leaderboard has added two private conversational English splits from Liva AI: Egyptian (1.34 hours) and Nigerian (1.55 hours). The Private tab will also report accent results using Kachru's Three Circles framework.

October 28, 2026
model releaseNVIDIA

NVIDIA Nemotron 3.5 Transcribe: open 30B model handles 40 languages, diarization and translation

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.

October 26, 2026
model releaseIflytek

iFLYTEK SparkAudio 1.0 speech model supports 99 languages and 202 dialects, pairs 0.65B encoder with 30B-A3B MoE

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.

October 21, 2026
model releaseIBM

IBM Granite Speech 5.0 2B ranks #2 among open ASR models at 5.06% WER under Apache 2.0

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.

September 23, 2026
model release

Alibaba Launches Qwen-Audio-3.1, Cuts AI Audio API Prices by Up to 95 Percent

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.

September 6, 2026
model releaseMicrosoft

Microsoft Releases VibeVoice-ASR-Streaming-7B, an Open-Weight Streaming Speech Recognition Model with Speaker Attributio

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.

August 25, 2026
model releaseIBM

IBM Releases Granite Speech 5.0 Turbo CTC: 470M-Parameter ASR Model Hits 12,600x Real-Time Speed

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.

July 29, 2026
model releaseOpenAI

OpenAI's GPT Transcribe Cuts Word Error Rate to 3.31% but Trails ElevenLabs, Google, and Mistral

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.