Voice Control Your
AI Agent Across
Every App

OpenClaw Does Everything. You Still Have to Type.

OpenClaw is the open-source AI agent that connects to your entire digital life — WhatsApp, Slack, Telegram, email, calendar, GitHub, and dozens more. It can send messages, schedule meetings, create issues, and manage your workflows. All from a single AI assistant.

But to use it, you type. Or you tap. Or you use its built-in voice wake word. The problem: OpenClaw's voice features are designed for conversational interactions, not rapid-fire task dispatch. You wait for it to wake, speak, wait for confirmation, confirm.

SpeechButton is different. Hold. Speak. Release.

The task hits OpenClaw's Gateway in under a second. No wake word. No confirmation dialog. No waiting.

How It Works: Voice → STT → Transform → OpenClaw Gateway

Your voice ──▶ SpeechButton STT ──▶ Transform ──▶ HTTP API ──▶ OpenClaw Agent
  (20ms)         (100% offline)      (Gemma 4)    (localhost)    (WhatsApp, Slack,
                                                                 Telegram, …)

OpenClaw exposes an OpenAI-compatible HTTP API on localhost. SpeechButton's exec field runs a simple curl command to post your structured task directly to the OpenClaw gateway.

Each piece is simple:

1. SpeechButton captures your voice and transcribes it locally (Apple Neural Engine, 100% offline)
2. Transform (Gemma 4) cleans and structures your spoken command locally
3. Exec script sends the structured task to OpenClaw's HTTP API via curl
4. OpenClaw agent receives and executes it across WhatsApp, Slack, Telegram, and 30+ platforms

The API is OpenAI-compatible — standard JSON, Bearer token auth, streaming support. No special SDK needed.

Setup

Prerequisites, config, and an exec script. Three files, five minutes.

# ~/.config/speechbutton/config.toml

[global]
model = "parakeet-tdt-0.6b-v3-int8"
language = "en"
auto_punctuation = true

[vad]
enabled = true
chunk_silence_sec = 1.0

# Send to OpenClaw agent via HTTP API
[[hotkey]]
key = "RightCommand"
channel = "9"
name = "openclaw"
transform = "__local__"
exec = "integrations/send_openclaw.py"

#!/usr/bin/env python3
"""Send voice command to OpenClaw agent via HTTP API."""
import sys, json, urllib.request, os

OPENCLAW_URL = os.getenv("OPENCLAW_URL", "http://127.0.0.1:18789")
OPENCLAW_TOKEN = os.getenv("OPENCLAW_GATEWAY_TOKEN", "")
SESSION_KEY = sys.argv[1] if len(sys.argv) > 1 else "speechbutton"

text = sys.stdin.read().strip()
if not text:
    sys.exit(0)

payload = json.dumps({
    "model": "openclaw/default",
    "messages": [{"role": "user", "content": text}]
}).encode()

req = urllib.request.Request(
    f"{OPENCLAW_URL}/v1/chat/completions",
    data=payload,
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {OPENCLAW_TOKEN}",
        "x-openclaw-session-key": SESSION_KEY,
    }
)
urllib.request.urlopen(req)

# prompts/default.md
# Default transform — clean up spoken input for an AI agent

Clean up this spoken command for an AI agent.
Fix grammar, remove filler words, make the
instruction clear and actionable.
Output ONLY the cleaned command.

# RightCommand+9 → PM agent (with AI transform)
[[hotkey]]
key = "RightCommand"
channel = "9"
name = "openclaw-pm"
transform = "prompts/default.md"
exec = "integrations/send_openclaw.py"

# RightCommand+0 → Dev agent (with task-specific transform)
[[hotkey]]
key = "RightCommand"
channel = "1"
name = "openclaw-dev"
transform = "prompts/claude_code_task.md"
exec = "integrations/send_openclaw.py dev"

Real Workflows

You're deep in work. OpenClaw handles the communications layer. Your voice is the interface.

Cross-platform messaging without opening anything

You need to reach people on different platforms. Normally: open WhatsApp, type. Open Slack, type. Open Telegram, type.

Three platforms. Three messages. 20 seconds of speaking. Zero app switching.

Multi-step tasks

OpenClaw can chain actions. Your voice triggers complex workflows:

OpenClaw handles the calendar creation, the invites, and the Slack notification. You spoke one sentence.

Morning briefing

OpenClaw scans your messaging platforms, summarizes, and responds. You're briefed while making coffee.

Quick replies while coding

Someone messages you. You don't want to context-switch.

Command+6 is your raw-message channel. No transform, no overhead. Dispatched through OpenClaw in two seconds.

Why SpeechButton + OpenClaw > OpenClaw Alone

OpenClaw already has voice features — Voice Wake and Talk Mode. Why add SpeechButton?

SpeechButton is for rapid-fire task dispatch — you know what you want, you say it, it's done. OpenClaw's built-in voice is for conversational interactions where you need back-and-forth. They complement each other.

The per-hotkey routing is the key differentiator. Command+5 for agent tasks, Command+6 for quick messages, Command+2 for Slack (directly, bypassing OpenClaw), Command+3 for Linear. You choose the optimal path per command — sometimes through OpenClaw, sometimes direct.

Privacy

Here's exactly what stays on your Mac and what goes to external services:

Voice capture, STT, and the AI transform are 100% local — no audio ever leaves your Mac. The task text is sent to OpenClaw's gateway on localhost (127.0.0.1) — it never touches the internet until OpenClaw executes the task on your chosen platform.

Get Started