DavidROliverBA/ArchitectKB / .claude/skills/voice-chat
voice-chat
VerifiedVoice-controlled Claude Code - speak commands, hear responses in Olivia voice
/voice-chat
Voice-controlled Claude Code. Speak your commands/questions, Claude processes them verbatim (as if you typed them), and responds with Inworld Olivia voice.
Usage
/voice-chat # Start voice-controlled mode
/voice-chat stop # Exit voice mode
Requirements (from .claude/voice-chat-requirements.md)
R1: Voice Input β Claude Code Verbatim
Your spoken words are transcribed and passed directly to Claude Code β exactly as if you typed them.
R2: Response in Inworld Olivia Voice
Claude Code's response is spoken using Inworld TTS with Olivia voice.
Prerequisites
-
voice-bridge server running with
INWORLD_API_KEYset:cd ~/Documents/GitHub/voice-bridge VOICE_BACKEND=inworld INWORLD_API_KEY=<your-key> npm start -
Microphone permissions granted
Instructions
Starting Voice Mode
When /voice-chat is invoked:
-
Announce start:
mcp__voice-mcp__voice_speak({ text: "Voice mode active. Speak your command.", voice_id: "Olivia", speed: 1.0 }) -
Display:
π€ **Listening...** -
Listen for voice:
mcp__voice-mcp__voice_listen({ timeout_seconds: 30, language: "en-GB" }) -
Display the transcription:
π€ **You said:** "<transcribed text>" -
CRITICAL: Process the transcribed text as if the user typed it directly.
- Do NOT interpret it as a "voice chat question"
- Execute it as a normal Claude Code command/request
- Use all available tools (Read, Edit, Grep, Bash, etc.) as needed
- Generate your normal response
-
Display speaking indicator:
π **Speaking...** -
Speak the response (or summary if long):
mcp__voice-mcp__voice_speak({ text: "<response or summary>", voice_id: "Olivia", speed: 1.0, wait: true }) -
Smart Output Router - Decide what to speak:
Content Type Action Voice Says Short (< 100 words) Speak fully Full response Medium (100-300 words) Display + announce "Here's what I found" Long (> 300 words) Display only "Please read this" Contains code Display + announce "Here's the code" Contains table Display + announce "Here's a table" Error Speak Brief error description -
Loop back to step 2 for next command
Exit Conditions
- User says: "stop", "exit", "bye", "goodbye", "end voice mode"
- User types:
/voice-chat stop - Timeout with no input
Stopping Voice Mode
mcp__voice-mcp__voice_speak({
text: "Voice mode ended.",
voice_id: "Olivia",
speed: 1.0
})
Display: π **Voice mode ended.** Returning to text input.
Example Flow
User: /voice-chat
π€ **Listening...**
Olivia: "Voice mode active. Speak your command."
[User speaks: "What projects am I working on?"]
π€ **You said:** "What projects am I working on?"
[Claude searches vault, finds projects]
π **Speaking...**
π€ **Claude:** You have 3 active projects: Alpha, Beta, and Gamma.
Olivia: "You have 3 active projects: Alpha, Beta, and Gamma."
π€ **Listening...**
[User speaks: "Create a meeting note for today"]
π€ **You said:** "Create a meeting note for today"
[Claude creates meeting note using normal workflow]
π **Speaking...**
π€ **Claude:** Created Meeting - 2026-01-29 [Title].md
Olivia: "Meeting note created."
π€ **Listening...**
[User speaks: "Stop"]
Olivia: "Voice mode ended."
π **Voice mode ended.** Returning to text input.
Key Principle
The transcribed text IS the user's command. Process it exactly as you would if they typed it. The only difference is:
- Input comes from voice transcription
- Output is spoken via Inworld Olivia TTS
Troubleshooting
- Male voice playing: Check
INWORLD_API_KEYis set and voice-bridge restarted - No voice at all: Check voice-bridge is running on port 4000
- TTS error: Verify API key is valid base64-encoded Inworld key
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why β repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" β or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself β your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |