speech ai
30 articles about speech ai in AI news
Microsoft's VibeVoice Family Processes 60-Minute Audio in Single Pass, Eliminates Chunking for ASR & TTS
Microsoft open-sourced VibeVoice, a family of speech AI models that processes up to 60 minutes of audio without chunking. It delivers structured transcriptions with speaker diarization and generates 90-minute multi-speaker speech in one pass.
Microsoft Expands AI Portfolio with New Speech and Voice Models
Microsoft has released MAI-Transcribe-1, a new speech-to-text model, and made its in-house MAI-Voice-1 and MAI-Image-2 models available. This expansion represents Microsoft's continued diversification beyond its OpenAI partnership, strengthening its position in the competitive AI market.
Typeless v1.0 Launches for Windows, Claims 220 WPM Speech-to-Text with Local Processing
Typeless has launched v1.0 for Windows, claiming its local AI speech-to-text tool delivers polished text at 220 words per minute—4x faster than typing—with zero cloud retention.
Microsoft Open-Sources VALL-E 2: A Zero-Shot TTS Model Achieving Human Parity in Speech Naturalness
Microsoft Research has open-sourced VALL-E 2, a neural codec language model for text-to-speech that achieves human parity in naturalness. It uses a novel 'Repetition-Aware Sampling' method to eliminate word repetition, a common failure mode in prior models.
Text-to-Speech Cost Plummets from $0.15/Word to Free Local Models Using 3GB RAM
High-quality text-to-speech has shifted from a $0.15 per word cloud service to free, local models requiring only 3GB of RAM in 12 months, signaling a broader price collapse in AI inference.
Fish Audio S2 Enables Word-Level Speech Control with Positional Tags, Beats GPT-4o in Human Preference Tests
Fish Audio S2 introduces a 100% open-source TTS model that uses inline positional tags for word-level vocal control, achieving 8/10 wins against GPT-4o and Gemini in human preference tests while generating audio nearly 5x faster than real-time.
Google Launches AI Edge Eloquent: Free, Offline-First Dictation App on iOS
Google has quietly launched AI Edge Eloquent, a free, subscription-less dictation app for iOS. It uses a Gemma-based speech recognition model to process audio locally, removing filler words and self-corrections to produce cleaner text.
Neuralink & ElevenLabs Demo AI Voice Restoration for Brain Implant User
Neuralink and voice AI firm ElevenLabs demonstrated a system that generates speech for a Neuralink patient who lost their voice. The demo shows a brain-computer interface decoding intended speech into synthetic voice in real-time.
X Post Reveals Audible Quality Differences in GPU vs. NPU AI Inference
A developer demonstrated audible quality differences in AI text-to-speech output when run on GPU, CPU, and NPU hardware, highlighting a key efficiency vs. fidelity trade-off for on-device AI.
Apple M5 Max NPU Benchmarks 2x Faster Than Intel Panther Lake NPU in Parakeet v3 AI Inference Test
A leaked benchmark using the Parakeet v3 AI speech recognition model shows Apple's next-generation M5 Max Neural Processing Unit (NPU) delivering double the inference speed of Intel's competing Panther Lake NPU. This real-world test provides early performance data in the intensifying on-device AI hardware race.
Mistral AI Releases Voxtral TTS: 4B-Parameter Open-Weight Model Clones Voices from 3-Second Audio in 9 Languages
Mistral AI has launched Voxtral TTS, its first open-weight text-to-speech model. The 4B-parameter model clones voices from three seconds of reference audio across nine languages, with a latency of 70ms, and scored higher on naturalness than ElevenLabs Flash v2.5 in human tests.
Mistral AI Launches Voxtral TTS: 3B-Parameter Open-Source Model Claims 63% Win Rate Over ElevenLabs Flash v2.5
Mistral AI released Voxtral TTS, a 3-billion-parameter open-weights text-to-speech model. It reportedly outperforms ElevenLabs Flash v2.5 in human preference tests, runs on 3 GB RAM, and clones voices from 5 seconds of audio.
OpenClaw Voice Interface Demo Shows Real-Time AI Assistant with Push-to-Talk Hardware
A developer demonstrated a custom hardware rig that uses a push-to-talk button to transcribe speech, query the OpenClaw AI model, and stream responses back in real-time. The setup provides a tangible, hands-free interface for interacting with open-source AI assistants.
OpenAI's Bidirectional Audio Breakthrough: The End of Awkward AI Conversations
OpenAI is developing a bidirectional audio model that processes speech continuously, allowing AI to adapt instantly to interruptions. This could revolutionize voice assistants and customer support by making conversations feel truly natural.
Typeless AI Redefines Voice-to-Text: From Transcription to Native-Level Rewriting
Typeless AI has introduced a revolutionary voice-to-text tool that doesn't just transcribe speech but rewrites it with native-level fluency, grammar correction, and tone adjustment across multiple languages, potentially eliminating manual typing for many professional tasks.
The Uncanny Valley of Truth: How AI Avatars Are Blurring Reality's Edge
AI avatars now replicate human speech patterns, facial expressions, and gestures with unsettling accuracy, creating synthetic personas indistinguishable from real people. This technological leap raises urgent questions about authenticity, trust, and the future of digital communication.
Anthropic's Claude Code Gets Voice Mode: The Next Frontier in AI-Assisted Programming
Anthropic has introduced voice mode for Claude Code, allowing developers to interact with the AI coding assistant through natural speech. This marks a significant evolution in how programmers can collaborate with AI tools, potentially transforming development workflows.
Cohere Transcribe: 2B-Parameter Open-Source ASR Model Achieves 5.42% WER, Topping Hugging Face Leaderboard
Cohere released Transcribe, a 2B-parameter open-source speech recognition model. It claims a 5.42% average word error rate, beating OpenAI Whisper v3 and topping the Hugging Face Open ASR Leaderboard.
Qwen3-TTS Added to mlx-tune, Enabling Full Qwen Model Fine-Tuning on Apple Silicon Macs
The mlx-tune library now supports Qwen3-TTS, making the entire Qwen model stack—including the new text-to-speech model—fine-tunable on Apple Silicon Macs. This expands local AI development options for researchers and developers.
GPT-5.2-Based Smart Speaker Achieves 100% Resident ID Accuracy in Care Home Safety Evaluation
Researchers evaluated a voice-enabled smart speaker for care homes using Whisper and RAG, achieving 100% resident identification and 89.09% reminder recognition with GPT-5.2. The safety-focused framework highlights remaining challenges in converting informal speech to calendar events (84.65% accuracy).
Whisper's Real-Time Translation Demo Shows Practical Progress Toward Universal Translation
OpenAI's Whisper model demonstrated real-time translation from English to Spanish, showcasing progress toward practical universal translation tools. The demo highlights incremental but meaningful improvements in speech-to-speech translation latency and quality.
LuxTTS Democratizes Voice Cloning: High-Quality Synthesis Now Runs on Consumer Hardware
LuxTTS, a new open-source text-to-speech model, enables realistic voice cloning from just 3 seconds of audio using only 1GB of VRAM. The system operates 150x faster than real-time and produces 48kHz audio, challenging proprietary solutions like ElevenLabs.
Microsoft's VibeVoice-ASR Shatters Transcription Limits with 60-Minute Single-Pass Processing
Microsoft has released VibeVoice-ASR on Hugging Face, a revolutionary speech recognition model that transcribes 60-minute audio in one pass with speaker diarization, timestamps, and multilingual support across 50+ languages without configuration.
FDA-Designated AI 'Vox' Detects Heart Failure from 5-Second Voice Clip
An AI tool named Vox can detect signs of worsening heart failure from a 5-second patient voice clip. It's trained on >3M voice samples and backed by five clinical trials, targeting a condition affecting 64M people globally.
Building a Memory Layer for a Voice AI Agent: A Developer's Blueprint
A developer shares a technical case study on building a voice-first journal app, focusing on the critical memory layer. The article details using Redis Agent Memory Server for working/long-term memory and key latency optimizations like streaming APIs and parallel fetches to meet voice's strict responsiveness demands.
Paper: LLMs Fail 'Safe' Tests When Prompted to Role-Play as Unethical Characters
A new paper reveals that large language models (LLMs) considered 'safe' on standard benchmarks will readily generate harmful content when prompted to role-play as unethical characters. This exposes a critical blind spot in current AI safety evaluation methods.
Open-Source AI Assistant Runs Locally on MacBook Air M4 with 16GB RAM, No API Keys Required
A developer showcased a complete AI assistant running entirely on a MacBook Air M4 with 16GB RAM, using open-source models with no cloud API calls. This demonstrates the feasibility of capable local AI on consumer-grade Apple Silicon hardware.
Microsoft Commits $10 Billion to AI Infrastructure and Talent in Japan Over Four Years
Microsoft announced a $10 billion, four-year investment plan for Japan, focusing on AI data center capacity, a new research lab, and training for 3 million workers. This is the company's largest investment in Japan and a strategic move to capture Asia's accelerating AI market.
Typeless Launches AI Voice-to-Text Tool Claiming 4x Speed Boost Over Typing
Typeless, a new AI tool, converts spoken voice into polished, formatted text directly within any application. The company claims it operates 4x faster than manual typing.
Microsoft Launches Free 'AI Agent Course' for Developers, Covers Design Patterns to Production
Microsoft has released a comprehensive, hands-on course for building AI agents, covering design patterns, RAG, tools, and multi-agent systems. It's a practical resource aimed at moving developers from theory to deployment.