voice-ai-integration · qodex-ai — Claude Code skill: speech recognition and TTS
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.
no license 211 installs ★ 50 updated 2026-01-05
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a claude-codeWhat voice-ai-integration 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.
What it helps with
- 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 for the agent
- Build a voice assistant on
VoiceAssistantwith Whisper for input and ElevenLabs for the reply. - Add voice activity detection to
examples/realtime_voice_processor.pyand play the answer through the speakers. - Transcribe the meeting in 30-second chunks and keep the timestamps.
How to install voice-ai-integration
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a claude-code2Manually: put the files in place
~/.claude/skills/voice-ai-integration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/voice-ai-integration/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a codex2Manually: put the files in place
.agents/skills/voice-ai-integration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a cursor2Manually: put the files in place
.cursor/skills/voice-ai-integration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install qodex-ai/ai-agent-skills skills/voice-ai-integration2Manually: put the files in place
.github/skills/voice-ai-integration/SKILL.md1Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a gemini-cli2Platform CLI
gemini skills install https://github.com/qodex-ai/ai-agent-skills --path skills/voice-ai-integrationManually: put the files in place
.devin/skills/voice-ai-integration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about voice-ai-integration
How do I install voice-ai-integration in Claude Code?
Run npx skills add qodex-ai/ai-agent-skills --skill voice-ai-integration -a claude-code. The skill file lands at ~/.claude/skills/voice-ai-integration/SKILL.md.
What does voice-ai-integration do?
It walks through building a voice app: recognising speech, parsing the intent, then synthesising a spoken answer. Python examples for several providers come with it, plus a VoiceAssistant class that tracks the dialogue.
Which providers can I use?
Recognition: Google Cloud, Whisper, Azure, AssemblyAI. Synthesis: Google Cloud TTS, OpenAI TTS, Azure, ElevenLabs.
Similar skills
All skills for AI and ML →voice-ai-integration by other authors comes first.