voice-reply
Generate voice replies using OpenAI TTS API and send audio responses.
npx skills add majiayu000/claude-skill-registry --skill voice-reply-leovigna-jarvis-template --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Voice Reply Skill Generate spoken audio responses using OpenAI's Text-to-Speech API. ## When to Use 1. When the user asks to "reply by voice", "voice reply", "speak this", or similar voice-related requests. 2. **Command trigger:** When user sends `/voice_note`, resend the last message as a voice note. - **Remove all emojis** from the text before converting to speech - **Rephrase if needed** to make it sound natural when spoken (e.g., convert bullet points to flowing sentences) ## How to Use ### 1. Prepare the Response Write your response **without emojis** — they don't translate well to speech. ### 2. Generate Audio **Important:** Use `opus` format for Telegram voice notes (shows waveform bubble). ```bash curl https://api.openai.com/v1/audio/speech \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4o-mini-tts", "input": "<your text here>", "voice": "echo", "speed": 1.2, "response_format": "opus" }' -s --output /tmp/voice_reply.ogg ``` ### 3. Send the Audio Copy to outbound folder and send via message tool: ```bash mkdir -p /home/exedev/.clawdbot/media/outbound cp /tmp/voice_reply.ogg /home/exedev/.clawdbot/media/outbound/voic
- When to Use
- How to Use
- 1. Prepare the Response
- 2. Generate Audio
- 3. Send the Audio
- Configuration Options
- Voice Options
- Speed
- Model
- Example Workflow
- Tips
- References
curl https://api.openai.com/v1/audio/speech \ mkdir -p /home/exedev/.clawdbot/media/outbound cp /tmp/voice_reply.ogg /home/exedev/.clawdbot/media/outbound/voice_reply.ogg cp /tmp/reply.ogg ~/.clawdbot/media/outbound/reply.ogg
What does the voice-reply skill do?
Generate voice replies using OpenAI TTS API and send audio responses.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill voice-reply-leovigna-jarvis-template --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.