# voice-agents

Walks you through picking a voice agent architecture, budgeting latency and handling interruptions without awkward pauses.

- skill · `type=skill` · Claude Code · 194 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/voice-agents
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/voice-agents

## What it does

The skill lays out two ways to build a voice agent. Speech-to-speech on the OpenAI Realtime API sends audio straight to audio: lowest latency, emotion preserved, less control. The pipeline route runs STT→LLM→TTS, so every step stays inspectable and easier to debug, at the cost of added milliseconds.

Its core point: latency is the constraint. Each component contributes its own delay, and the total decides whether a conversation feels natural. So the skill tells you to measure and budget latency per component first, before picking models.

Inside are patterns for voice activity detection, barge-in detection and turn-taking, plus a list of anti-patterns. The sharp edges get their own section: turn detection that only listens for silence, long responses, background noise, STT errors. It pairs with `agent-tool-builder`, `multi-agent-orchestration`, `llm-architect` and `backend`.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill ai-research/voice-agents
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill voice-agents -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/voice-agents/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/voice-agents/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/voice-agents/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/voice-agents/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates voice-agents
```

2. **Manually: put the files in place**
- File: `.github/skills/voice-agents/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/ai-research/voice-agents
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/voice-agents/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/ai-research/voice-agents

## When to use it
- choose between speech-to-speech and an STT→LLM→TTS pipeline
- budget latency across every component in the chain
- set up voice activity detection and turn-taking
- detect barge-in so the agent stops talking when interrupted
- keep agent replies short and spoken-friendly

## Example prompts
- help me design a voice agent on the Anthropic Realtime API
- break down latency per component in an STT→LLM→TTS pipeline
- how do I implement barge-in detection in a voice agent

## Similar
- [speech-engine](https://affpapa.org/en/nevibecode/skills/speech-engine.md) — skill · 6500 installs
- [voicemode](https://affpapa.org/en/nevibecode/mcp/voicemode.md) — MCP server · ★ 1417
- [speakturbo-tts](https://affpapa.org/en/nevibecode/skills/speakturbo-tts.md) — skill · 1000 installs
- [characteristic-voice](https://affpapa.org/en/nevibecode/skills/characteristic-voice.md) — skill · 2800 installs
- [voice-audio-engineer](https://affpapa.org/en/nevibecode/skills/voice-audio-engineer.md) — skill · 367 installs
- [add-voice](https://affpapa.org/en/nevibecode/skills/add-voice.md) — skill · 319 installs

## Other versions with the same name
- [voice-agents · sickn33](https://affpapa.org/en/nevibecode/skills/sickn33-voice-agents.md) — 890 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 224 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md