A developer compared OpenAI's Realtime API with LiveKit for enterprise voice agents, highlighting trade-offs in latency, cost, and compliance. The analysis shows LiveKit's modular WebRTC pipeline can …
FunASR, an industrial-grade speech recognition toolkit, released an update in August 2026, achieving up to 340x realtime speed and 26x faster than Whisper, supporting 50+ languages, speaker diarizatio…
A developer released claude-real-video, an open-source tool that lets AI agents like Claude Desktop and Cursor watch videos by extracting scene-aware keyframes and timestamped transcripts locally. The…
Hugging Face has released an open-source server that replicates OpenAI's Realtime API protocol, enabling developers to run a local speech-to-speech pipeline compatible with OpenAI's WebSocket interfac…
A self-hosted speech pipeline using a layered architecture achieves 0.91 medical-term recall on German consultations, outperforming AWS Transcribe's 0.82 baseline while keeping audio on-premise. The r…
Minute released a privacy-first macOS app for offline meeting transcription that captures audio, transcribes locally with Whisper, and generates summaries using local llama.cpp, avoiding cloud exposur…
A developer released Minute, a macOS app that transcribes and summarizes meetings offline using local Whisper and llama.cpp models, with no cloud dependency or telemetry. Built with Tauri, Rust, React…
Brain, a local-first knowledge base tool that turns YouTube talks, podcasts, arXiv papers, and other content into searchable Markdown notes, has been released as an open-source project on GitHub. The …
DictaFlow's Local Offline Mode enables dictation on Windows, Apple silicon Macs, and iPhones without an internet connection using on-device models like NVIDIA's Parakeet TDT 0.6B v3, while competitor …
ARIA, a voice-native 3D spatial AI security operations cockpit with governed autonomy, is now available under BSL 1.1 for evaluation and research. Developed by a solo developer, the platform runs enti…
A developer's claude-real-video tool lets any LLM watch videos by extracting scene-aware keyframes with timestamps and a timestamped transcript, bypassing middleman models. The tool, which runs locall…
Solo developer Owen Song released Inflect-Micro-v2 on July 24, 2026, a 9,356,513-parameter text-to-speech model that generates 24 kHz waveforms from English text without a hosted service or separate n…
A new automatic speech recognition model, Diffusion-gemma-asr, achieves 15x faster inference than OpenAI's Whisper by freezing a Whisper-small encoder and DiffusionGemma weights and adding a 42M param…
A developer built a pipeline using OpenAI's Whisper and GPT-4o-mini to analyze radio ad density across 11 stations, finding that ad breaks spike at the top of the hour and multiple stations often run …
A developer shipping three browser-based AI tools—a stem splitter using Meta's HTDemucs, a Whisper speech-to-text model, and a third unnamed tool—found that model corruption, ONNX Runtime graph optimi…
A developer built WeConvertIt, a suite of three AI tools that run entirely in the browser, and documented critical bugs encountered during development. A broken ONNX model for music stem separation wa…
Primate Labs released Geekbench 7, a major update to its cross-platform benchmarking tool, with new and improved workloads for CPUs and GPUs that better reflect real-world usage in 2026. The update in…
Oats, a free meeting-notes app for Mac, processes all audio and transcription locally using Whisper and Ollama, ensuring no data ever leaves the user's machine. The app, which supports optional cloud …
Jharu v0.2.0, a free open-source disk cleaner and storage analyzer for macOS and Windows, targets gigabytes of junk left by development tools and machine learning frameworks. The tool identifies and s…
Willow, a voice dictation startup, announced a new platform on July 23rd, 2026, that measures success by a "zero edit rate" — the proportion of transcriptions that require no user edits before sending…