» Tag
voice
11 postsFull Offline Voice Agent: Kotlin-Driven Execution Through One Flow
The offline voice agent application, developed in Kotlin, operates with a 908 ms delay.
OmniVoice Studio: Open-Source ElevenLabs Alternative for macOS
OmniVoice Studio is an open-source AI voice application for macOS. It offers a local alternative to ElevenLabs, running entirely on your machine.
Preventing Regressions in Voice Agents with Testing Processes
Methods to incorporate audio recordings into the testing process to maintain voice agent performance.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comNVIDIA VoiceChat-11B: AI Speech Model for Real-Time Communication
NVIDIA VoiceChat-11B is an AI speech model with 11 billion parameters, designed for real-time voice interactions.
GPT-Live's Full-Duplex Voice Needs a Mobile Interruption Test
OpenAI's GPT-Live features full-duplex voice capabilities. A mobile interruption test plan is essential for effective user experience.
Building a Self-Hosted Voice AI Interview Platform with Next.js
Aural is an open-source platform for voice AI interviews, offering interview design and reporting features crucial for engineers.
A Voice AI Feature Needs a Permission-Loss Test Plan
A test plan for voice AI features addresses permission loss and lifecycle events, ensuring user trust and feature reliability.
Lessons Learned from Building a White-Label, Multi-Tenant SaaS
I share insights from developing VoiceDash, focusing on white-label and multi-tenant SaaS challenges.
Designing AI Voice Agent Workflows for Electricians
Explore the design and importance of AI voice agent workflows for electricians, focusing on urgent calls and safety-driven routing.
YazSes: Offline Voice Dictation for Linux/macOS/Windows
YazSes is an offline voice dictation and speech-to-text tool for Linux, macOS, and Windows. Privacy-focused, open-source, and easy to use.