Voice Agents
This is for building voice AI systems where humans talk naturally with AI and get responses fast enough that it doesn't feel broken. The core tradeoff is laid out clearly: speech-to-speech models like OpenAI's Realtime API give you the lowest latency and preserve emotion, but you sacrifice control. Pipeline architectures where you chain STT, LLM, and TTS let you debug and tune each piece, but every component adds milliseconds. The skill hammers on latency budgets because that's what separates demos from production. It covers the practical stuff like handling interruptions, dealing with background noise, and detecting when users start talking so the AI can shut up. If you're shipping something where 800ms response time is the difference between natural and awkward, this maps the territory.
- skills.sh installs
- 347
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill voice-agents --agent claude-codeInstalls into .claude/skills of the current project.
Files
Voice Agents
You are a voice AI architect who has shipped production voice agents handling millions of calls. You understand the physics of latency - every component adds milliseconds, and the sum determines whether conversations feel natural or awkward.
Your core insight: Two architectures exist. Speech-to-speech (S2S) models like OpenAI Realtime API preserve emotion and achieve lowest latency but are less controllable. Pipeline architectures (STT→LLM→TTS) give you control at each step but add latency. Mos
Capabilities
- voice-agents
- speech-to-speech
- speech-to-text
- text-to-speech
- conversational-ai
- voice-activity-detection
- turn-taking
- barge-in-detection
- voice-interfaces
Patterns
Speech-to-Speech Architecture
Direct audio-to-audio processing for lowest latency
Pipeline Architecture
Separate STT → LLM → TTS for maximum control
Voice Activity Detection Pattern
Detect when user starts/stops speaking
Anti-Patterns
❌ Ignoring Latency Budget
❌ Silence-Only Turn Detection
❌ Long Responses
⚠️ Sharp Edges
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davila7/claude-code-templates
- Categories
- Backend & APIs, DevOps & CI/CD, AI & Agent Building, Debugging, Automation & Workflows, Sales & Marketing, Design & UI/UX, Generative Media
- First seen
- Jun 3, 2026
More from davila7/claude-code-templates
All 618- Git Pushing346
- Brand Guidelines344
- Paid Ads344
- Guidance343
- Executing Plans342
- Launch Strategy342
- Marp Slide342
- Writing Clearly And Concisely342
- Browser Extension Builder341
- Huggingface Tokenizers340
- Llama Factory339
- Stable Baselines3338
- Bullmq Specialist337
- Crewai337
- Quantizing Models Bitsandbytes337
- Nemo Curator336
- Discord Bot Architect335
- Railway Deploy335
- Aws Serverless334
- Clip334
- Datadog Cli334
- Lint And Validate334
- Notion Meeting Intelligence334
- Speculative Decoding334
Recommended
More Backend & APIs
training-log-analyzeronewave-ai/claude-skillsTrack workouts, stats, progress over time. Identify improvement areas, plateaus, rest/recovery needs, peak performance timing, injury risk.347skills.sh installs
feishu-send-filerabbitmeaw/feishu-send-fileSend files, images, and audio messages via Feishu Lark API using the mandatory two-step process. Use when needing to send files, images, or voice messages to Fe347skills.sh installs
skywork-music-makerskyworkai/skywork-skillsCreate professional music with Mureka AI API — songs, instrumentals, and lyrics from natural language descriptions in any language. Use when users want to gener345skills.sh installs
performance-smell-detectiondecebals/claude-code-javaDetect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measur341skills.sh installs
audio-voice-recoverypproenca/dot-skillsAudio forensics and voice recovery guidelines for CSI-level audio analysis. This skill should be used when recovering voice from low-quality or low-volume audio340skills.sh installs
react-query-best-practicesarraydude/agent-skillsReact Query v4 (TanStack Query) best practices, patterns, and troubleshooting. Use when working with useQuery, useMutation, query invalidation, caching, WebSock339skills.sh installs