respond-with-voice

Reply to the user with a voice note instead of (or in addition to) text.

IndexedMIT★ 5

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/techfreakworm-respond-with-voice

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Reply to the user with a voice note instead of (or in addition to) text. Use when: (a) the incoming user message had `voice_in: true` meta (mirror modality), (b) the user explicitly asked for a voice reply, or (c) the reply is short plain language that is voice-friendly. DO NOT use when the reply contains code blocks, tables, URLs the user needs to copy, or anything longer than ~3 sentences.

Use cases: writing, productivity

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/respond-with-voice

Tools it pre-approves 2

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

mcp__voice-tts__synthesize,
mcp__telegram__reply_voice

What's inside

Skill name: respond-with-voice
Description: Reply to the user with a voice note instead of (or in addition to) text. Use when: (a) the incoming user message had `voice_in: true` meta (mirror modality), (b) the user explicitly asked for a voice reply, or (c) the reply is short plain language that is voice-friendly. DO NOT use when the reply contains code blocks, tables, URLs the user needs to copy, or anything longer than ~3 sentences.
License: MIT
Allowed tools: mcp__voice-tts__synthesize,, mcp__telegram__reply_voice
Instructions: 27 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# respond-with-voice

When invoked, you have a `reply_text` you want to deliver as audio.

1. Call `mcp__voice-tts__synthesize` with `text=<reply_text>`. This returns
   `{audio_path, duration_seconds, voice_used}`.

2. Call `mcp__telegram__reply_voice` (provided by the telegram channel plugin)
   with `audio_path=<the path from step 1>`. The channel uploads it as a
   Telegram voice note in the current chat.

3. If the reply ALSO contains a code block, a long table, or a URL the user
   needs to copy/click, additionally send those parts as text via the channel's
   normal text reply so the user has copy-pasteable material.

4. Confirm in plain language (one short sentence) that you've sent the voice.
   Do NOT also TTS this confirmation — it would create an echo loop.

## When not to call this skill

- Replies containing more than ~3 sentences of dense info — use text
- Code blocks, JSON, tables — use text
- Error messages with stack traces — use text
- When the user has explicitly disabled voice in this thread (check
  `/admin/conversations` for thread preferences)

From techfreakworm/claude-soma, MIT.

Signals

Stars: 5
Forks: 1
Open issues: 0
Last commit (this folder): May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/techfreakworm/claude-soma
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from techfreakworm

Cite this page

respond-with-voice skill. Agent Mart. https://agentmart.dev/skills/techfreakworm-respond-with-voice (last updated 2026-10-24)