Silero VAD
PulseAugur coverage of Silero VAD — every cluster mentioning Silero VAD across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Silero VAD endpointing issues cut off 23% of voice app answers
A voice application using Silero VAD experienced significant issues where its endpointing mechanism prematurely cut off user responses. The default 700ms silence detection threshold was too short for users who paused to…
-
ChatGPT Voice Mode Reportedly Uses Open-Source Silero VAD v6
OpenAI is reportedly utilizing the open-source Silero VAD v6 model for its ChatGPT voice mode. This choice suggests a move towards integrating existing, efficient open-source solutions rather than developing proprietary…
-
AI voice agent costs slashed to 2.5¢/min via custom pipeline
A company has detailed the cost breakdown of running its AI voice agent, which handles candidate interviews. By migrating from a managed voice platform to a custom LiveKit pipeline, they reduced costs from approximately…
-
AI systems developed for practicing workplace conversations and clinic reception
A voice-enabled AI system called Conversation Coach has been developed to help managers practice difficult workplace conversations, addressing challenges in low-latency interaction, adaptive bot personalities, and perso…
-
Developer fixes LLM video hallucinations with OCR and audio gates
A developer has improved their open-source tool, crv, by addressing issues with Large Language Models (LLMs) misinterpreting audio and video content. The tool now uses a voice-activity detection (VAD) gate with Whisper …
-
audio.cpp framework offers faster audio model inference
A new C++ inference framework called audio.cpp has been developed, built on top of ggml, to run various audio models including TTS, ASR, and voice conversion. The framework aims to consolidate multiple audio models into…
-
Offline voice loop for local AI models runs entirely on CPU
A developer has created a fully offline voice interaction loop for local AI models, utilizing only CPU resources and ensuring all data remains on the user's machine. This system integrates Silero VAD for voice activity …
-
Local ASR router uses specialized models for real-time multilingual transcription
A researcher at Gladia has developed a novel approach to real-time multilingual automatic speech recognition (ASR) that runs on local hardware. Instead of using a single, large model, the system employs a router that di…
-
New research tackles multilingual ASR challenges with novel approaches
Researchers are exploring new methods for multilingual Automatic Speech Recognition (ASR), particularly for code-switching scenarios where multiple languages are used within a single conversation. One paper investigates…
-
Hugging Face enables fully local Reachy Mini conversations
Hugging Face has released a guide detailing how to set up a fully local speech-to-speech conversation pipeline for the Reachy Mini robot. This setup utilizes a cascaded approach with recommended components like llama.cp…
-
WhisperPipe architecture slashes ASR latency and memory use for real-time applications
Researchers have developed WhisperPipe, a new streaming architecture designed to improve real-time automatic speech recognition (ASR) performance. This architecture addresses the trade-off between accuracy and computati…