🎙️ Whisper

speech-to-text, model, local, whisper, whisper.cpp, input, voice, recognition, ai

Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation
arxiv.org·8h
📝Concrete Syntax
Effective Practices for Coding with a Chat-Based AI
infoq.com·12h·
Discuss: Hacker News
🔄Language Evolution
Mistral launches Voxtral speech recognition model
theregister.com·1d
🎵Audio ML
IoT AI with Ioto
dev.to·8h·
Discuss: DEV
🎬WebCodecs API
This “smart coach” helps LLMs switch between text and code
news.mit.edu·8h
💻Local LLMs
Voxtral
mistral.ai·1d·
Discuss: Hacker News
🎧Learned Audio
WiSec 2025 Spotlight: Security in the Inaudible World
esat.kuleuven.be·22h
📡Bluetooth Archaeology
2025-07-16: Understanding Hallucination in Large Language Models: Challenges and Opportunities
ws-dl.blogspot.com·11h·
Discuss: ws-dl.blogspot.com
✨Effect Handlers
Let AI Tune Your Voice Assistant
towardsdatascience.com·2d
⚡Proof Automation
My favorite use-case for AI is writing logs
vickiboykis.com·1d
🌳Incremental Parsing
MultiVox: Benchmarking Voice Assistants for Multimodal Interactions
arxiv.org·1d
🗣️CMU Pronouncing
How to actually use Model Context Protocol
seangoedecke.com·12h
⚡Proof Automation
Whisper API hallucinating on empty sections
community.openai.com·1d·
Discuss: Hacker News
🎧Vorbis Encoding
Build an Intelligent Slackbot That Knows Your Cloud: 4 Steps
thenewstack.io·16h
🏠Homelab Orchestration
Introduction: AI Terminology
dev.to·21h·
Discuss: DEV
🤖Grammar Induction
ASMR AI: Generate AI ASMR Videos with High Quality ASMR Voice
asmrai.net·6h·
Discuss: Hacker News
🎧Learned Audio
A Multimodal Data Fusion Generative Adversarial Network for Real Time Underwater Sound Speed Field Construction
arxiv.org·8h
🎧Vorbis Encoding
Advice on Building Voice AI in June 2025
daily.co·3d·
Discuss: Hacker News
🌊Stream Processing
Deploy conversational agents with Vonage and Amazon Nova Sonic
aws.amazon.com·17h
🌊Streaming Systems
Open-source framework for real-time AI voice
github.com·1d·
Discuss: Hacker News
🎬WebCodecs API