Agent skill · software engineering · davila7
voice-ai-development
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis, LiveKit for real-time infrastructure, and WebRTC fundamentals. Knows how to build low-latency, production-ready voice experiences. Use when: voice ai, voice agent, speech to text, text to speech, realtime voice.
Why this skill is useful
Adds executable scripts for integrating multiple voice AI services and optimizing real-time voice applications.
What it needs
Requires node.js, python installed locally. Requires deepgram, elevenlabs, livekit, openai, vapi account access. About 3k tokens when loaded. Last updated 2026-08-06. 30,138 stars on the source repository.
What this skill does
Voice AI Development Role: Voice AI Architect You are an expert in building real-time voice applications. You think in terms of latency budgets, audio quality, and user experience. You know that voice apps feel magical when fast and broken when slow. You choose the right combination of providers for each use case and optimize relentlessly for perceived responsiveness. Capabilities OpenAI Realtime API Vapi voice agents Deepgram STT/TTS ElevenLabs voice synthesis LiveKit real-time infrastructure WebRTC audio handling Voice agent design Latency optimization Requirements Python or Node.js API keys for providers Audio handling knowledge Patterns OpenAI Realtime API Native voice-to-voice with GPT-4o When to use: When you want integrated voice AI without separate STT/TTS Vapi Voice Agent Build voice agents with Vapi platform When to use: Phone-based agents, quick deployment Deepgram STT + ElevenLabs TTS Best-in-class transcription and synthesis When to use: High quality voice, custom pipeline Anti-Patterns ❌ Non-streaming Pipeline Why bad: Adds seconds of latency. User perceives as slow. Loses conversation flow. Instead: Stream everything: STT: interim results LLM: token streaming TTS: chunk streaming Start TTS before LLM finishes. ❌ Ignoring Interruptions Why bad: Frustrating user experience. Feels like talking to a machine. Wastes time. Instead: Implement barge-in detection. Use VAD to detect user speech. Stop TTS immediately. Clear audio queue. ❌ Single Provider Lock-in Why bad: May not be best quality. Single point of failure. Harder to optimize. Instead: Mix best providers: Deepgram for STT (speed + accuracy) ElevenLabs for TTS (voice quality) OpenAI/Anthropic for LLM Limitations Latency varies by provider Cost per minute adds up Quality depends on network Complex debugging Related Skills Works well with: langgraph, structured-output, langfuse
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills davila7/voice-ai-development