Social Media Ideas for Automatic Speech Recognition

Speech Recognition Explained: How Machines Understand Your Voice

Speech recognition—also known as Automatic Speech Recognition (ASR)—is the artificial intelligence technology that converts spoken human audio into written text in real time. Inste...

Best Open Speech Recognition (ASR) Models in 2026: WER, Languages, Latency, and License Compared

Open speech recognition stopped being a Whisper monoculture in 2026. Cohere Transcribe, IBM Granite Speech 4.1, ARK-ASR and MOSS-Transcribe are now separated by less than one WER p...

Building Voice-Controlled AI Agents

Building a voice-controlled AI agents isn't hard, this article breaks the pipeline into its real components: streaming speech recognition, turn detection, streaming generation, int...

PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling,...

PolyAI has introduced Dialog-RSN-1, a dialog model that perceives caller audio directly instead of reading an ASR transcript. It fuses turn-taking, speech recognition, function cal...

Meta launches Muse Voice Transcribe, MSL's first real-time audio perception model, with streaming automatic speech recog...

Meta AI Research: Meta launches Muse Voice Transcribe, MSL's first real-time audio perception model, with streaming automatic speech recognition, trained with 70+ languages  —  Exp...

9 Best Voice Recognition Software I Evaluated for 2026

I evaluated 20+ tools to find the 9 best voice recognition software for 2026. These include Deepgram, Google Cloud Speech-to-Text, Krisp, AssemblyAI - Speech to Text API, Otter.ai,...

Meta Superintelligence Labs Releases Muse Voice Transcribe: One Real-Time Model for Streaming ASR, Diarization, and Endp...

Most production voice stacks are three systems stitched together. One model transcribes, a second separates speakers, and a detector decides when the user stopped talking. Each han...

I built a portable keyword spotting engine — started with Chinese, now supporting English

I built a portable keyword spotting engine — started with Chinese, now supporting English I wanted offline voice commands for a few Python projects. Nothing fancy — just a si...

Cartesia Ships Sonic-3.6: A Streaming TTS Model That Now Leads Both Artificial Analysis Speech Arenas

Cartesia has released Sonic-3.6, a streaming text-to-speech model built on state space models rather than transformers. It now ranks #1 on both Artificial Analysis speech leaderboa...

Training Arabic Dialect TTS Models for On-Premises Voice AI: R&D Project by ScienceSoft

Meta、初のリアルタイム音声認識モデル「Muse Voice Transcribe」　20人超の話者識別と多言語混在に対応

Metaは、リアルタイム音声認識モデル「Muse Voice Transcribe」を発表した。単一モデルで音声認識、話者分離、発話終了検知を処理し、20人以上の話者識別や日本語を含む多言語に対応する。「Met...

Voice Recognition and Speech Synthesis on an RPi Pico 2

Pete Warden is on a mission to run a full voice interface on a fifty cent chip. This project hasn’t quite reached that goal but it is well on the way. Uses a Pi Pico with the help...

Meta's new AI transcription model can distinguish between multiple speakers and languages in real-time

The latest release from Meta Superintelligence Lab is a powerful transcription model.

How We Built a Production-Ready Speech-to-Text Feature in Flutter

Voice interfaces are becoming increasingly common in modern mobile applications. Whether users are searching for content, taking notes…Continue reading on Medium »

Humanoid robotics audio subsystem reference design

See how this reference design helps engineers build robot audio systems with voice capture, AI support, and microphone arrays. As humanoid robots become more capable, their audio s...

Voice-activity detection, speech to text, and text to speech all on RP2040

Pete Warden is convinced local voice interfaces and sub-$1 embedded chips will fundamentally change how we interact with everything in the physical world. I’m so excited to introdu...

Голосовой ввод в любое окно Windows за секунду. Офлайн, на CPU, без единого гигабайта torch

Голосовой ввод для Windows за ~1 секунду | Полностью локально • CPU • Open SourceКак заставить Whisper распознавать речь почти в 4 раза быстрее на обычном CPU без GPU и без облака....

AI Speech Neuroprosthesis Restores Voice to ALS Patient

Tested in an individual with advanced ALS, the interface enabled the real-time expression of 2.7 million words over two years, including vocal intonation modulation and singing, ma...

DevRev Voice AI empowers shared organizational memory across agents

Voice AI on Computer now takes live customer support calls

From 33% to 92%: What I Learned Building an Indian Language Speech Classifier

I trained CNNs, tried ImageNet and AudioSet transfer learning, tested Whisper zero-shot, and eventually fine-tuned Whisper on six Indian…Continue reading on Medium »

Getting Started with OmniVoice-Studio

OmniVoice Studio is built on a premise that everything runs on your hardware. Voice cloning, video dubbing, real-time dictation, voice design, all of it local, all of it free for p...

「えー」「あー」を除去して複数話者音声文字変換「Gemini 3.5 Transcribe」

Googleは26日(米国時間)、新しい高精度な音声文字変換モデル「Gemini 3.5 Transcribe」を発表した。背景のノイズなどの影響を低減し、音声データを正確で洗練されたテキストに変換できるほか、...

Представлена ИИ-модель M**a Muse Voice Transcribe для расшифровки речи

M**a представила первую модель искусственного интеллекта, предназначенную для обработки аудио в реальном времени. Muse Voice Transcribe расшифровывает речь для более чем 20 говорящ...

Voice Recognition Technology Is Here! And It Can Hear You!

Typically, as evidenced by the home automation industry’s active use of voice recognition for the consumer space, the consumer application of technologies, like virtual reality or...