voice-speak

Speak text into the active LiveKit voice bridge — TTS the assistant's reply into the room.

IndexedApache-2.0★ 6

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/glad-labs-voice-speak

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

Speak text into the active LiveKit voice bridge — TTS the assistant's reply into the room. Use when voice mode is on and the assistant wants to vocalize a reply, or when the user says "say this out loud".

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 and code. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Shell scripts

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/voice-speak

What's inside

Skill name: voice-speak
Description: Speak text into the active LiveKit voice bridge — TTS the assistant's reply into the room. Use when voice mode is on and the assistant wants to vocalize a reply, or when the user says "say this out loud".
License: Apache-2.0
Instructions: 33 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Files (2)

SKILL.md
run.sh · scripts/

SKILL.md (first lines)

# Voice Speak

TTS the given text into the active bridge session's LiveKit room. Long
replies (>500 chars by default — see `voice_bridge_chunk_max_chars`)
are chunked at sentence boundaries so the user can interrupt
mid-reply.

The session id is read from `~/.poindexter/voice/CURRENT_SESSION`
(written by `voice-on`). Override by passing the id explicitly as the
second argument.

## Usage

```bash
scripts/run.sh "<text to speak>" [session_id]
```

## Parameters

- **text** (string, required): What to TTS into the room.
- **session_id** (string, optional): Bridge session id. Defaults to
  whatever `voice-on` last wrote to
  `~/.poindexter/voice/CURRENT_SESSION`.

## Output

JSON object with:

- `status`: `"queued"` (success) or `"not_running"` (caller needs to re-`voice-on`)
- `session_id`: the bridge session that received the text
- `chunks`: number of TTS chunks emitted (sentence-bounded for interruptibility)

From Glad-Labs/poindexter, Apache-2.0.

Signals

Stars: 6
Forks: 2
Open issues: 31
Last commit (this folder): Jul 26, 2026 (3 months ago)
Last release: Oct 21, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/Glad-Labs/poindexter
Website: www.gladlabs.io
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Glad-Labs

Cite this page

voice-speak skill. Agent Mart. https://agentmart.dev/skills/glad-labs-voice-speak (last updated 2026-10-24)