# voice-ai-integration

voice-ai-integration turns spoken input into an answer: speech recognition, intent parsing, then a synthesized reply. Python examples for Whisper, Google Cloud, Azure and ElevenLabs.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 211 installs · ★ 50 repo stars
- Author: qodex-ai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qodex-ai/ai-agent-skills/tree/HEAD/skills/voice-ai-integration/SKILL.md
- Updated: 2026-01-05
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/qodex-ai-voice-ai-integration

## What it does

The pipeline this skill lays out has three stages: audio becomes text, the text is understood, the reply is spoken. Code samples are Python. `examples/speech_recognition_providers.py` wires up Google Cloud, Whisper, Azure and AssemblyAI, while `examples/text_to_speech_providers.py` covers Google Cloud TTS, OpenAI TTS, Azure and ElevenLabs. Conversation history and provider switching live in a `VoiceAssistant` class from `examples/voice_assistant.py`.

Live audio goes through `RealTimeVoiceProcessor` in `examples/realtime_voice_processor.py`. It takes microphone input and writes to speakers, runs voice activity detection, and lets you set the sample rate and chunk size. Two worked scenarios ship alongside: a smart home steered by spoken commands, and meeting capture that transcribes in slices.

Credentials come first. Without authentication for Google Cloud, Azure or ElevenLabs the pipeline does not start. For recognition the skill recommends 16 kHz audio and background noise filtering.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install qodex-ai/ai-agent-skills skills/voice-ai-integration
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/voice-ai-integration
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a opencode
```

### 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/qodex-ai/ai-agent-skills/tree/HEAD/skills/voice-ai-integration/SKILL.md

## When to use it
- wire speech-to-text, intent parsing and text-to-speech into one pipeline
- swap between Whisper, Google Cloud and Azure without rewriting the app
- stream microphone audio in fixed-size chunks
- drop silence with voice activity detection before it reaches the API
- transcribe a recorded meeting into timed slices

## Example prompts
- Build a voice assistant on `VoiceAssistant` with Whisper for input and ElevenLabs for the reply.
- Add voice activity detection to `examples/realtime_voice_processor.py` and play the answer through the speakers.
- Transcribe the meeting in 30-second chunks and keep the timestamps.

## Similar
- [voice-interface-builder](https://affpapa.org/en/nevibecode/skills/voice-interface-builder.md) — skill · 187 installs
- [voice-assistant](https://affpapa.org/en/nevibecode/agents/voice-assistant.md) — subagent · ★ 2858 repo stars
- [speech-engine](https://affpapa.org/en/nevibecode/skills/speech-engine.md) — skill · 9800 installs
- [voice-agents](https://affpapa.org/en/nevibecode/skills/sickn33-voice-agents.md) — skill · 904 installs
- [elevenlabs-tts](https://affpapa.org/en/nevibecode/skills/calesthio-elevenlabs-tts.md) — skill · 147 installs
- [eachlabs-voice-audio](https://affpapa.org/en/nevibecode/skills/eachlabs-voice-audio.md) — skill · 336 installs

## Other versions with the same name
- [voice-ai-integration · shengwang-community](https://affpapa.org/en/nevibecode/skills/voice-ai-integration.md) — 515 installs

From the same set: [qodex-ai/ai-agent-skills](https://affpapa.org/en/nevibecode/by/qodex-ai/ai-agent-skills.md) — 42 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
