SpeechButton — Push-to-Talk Speech-to-Text for macOS

Why SpeechButton

Everything runs on your Mac. No accounts, no servers, no cloud.

🔒

100% Private & Local

Your voice never leaves your Mac. Transcription runs entirely on the Apple Neural Engine via CoreML. No internet required.

🌍

25 Languages

Auto-detect and transcribe English, Spanish, French, German, Japanese, Chinese, and 19 more languages. Switch mid-sentence.

⚡

7ms Instant Capture

Press the key — recording starts in 7 milliseconds. Other apps take 200ms+ and lose the first word. SpeechButton captures everything from the very first syllable.

🛠

AI-Ready Text Config

All settings in a plain config.toml file. Hand it to an AI agent — it configures everything for you. Per-hotkey channel bindings, transform pipelines, device rules. Professional-grade control without a GUI.

Voice Activity Detection

Talk to AI agents.
Hands free.

SpeechButton transcribes in chunks as you speak. Every time you pause briefly, the chunk is transcribed and pasted instantly. When you finish talking, almost all text is already there.

With auto-Enter enabled, a longer silence (3s) sends the full message automatically. Hold the hotkey, talk to Claude Code or ChatGPT, pause briefly between thoughts — chunks appear in realtime. Stop talking for 3 seconds — message is sent. No keyboard needed.

# Hands-free voice activity detection
[vad]
enabled = true
chunk_silence_sec = 0.7    # pause → transcribe chunk

[global]
auto_send = true
send_delay_sec = 3.0      # 3s silence → auto-Enter

1

You speak

"Deploy the latest build to staging..."

2

Brief pause (0.5s)

Chunk 1 transcribed & pasted instantly

3

You continue speaking

"...and run the integration tests after"

4

Another pause → chunk 2 pasted

Previous text already there, only last chunk to process

✓

3s silence → auto-Enter

Full message sent. Zero wait time — text was already pasted in chunks.

What makes us different

Your Voice, Any Destination

SpeechButton doesn't just paste text at your cursor. It's a programmable voice pipeline — route, transform, and deliver your speech anywhere.

🔌

Hotkey Channels

Different key combos → different destinations. Hold Command and press 1, 2, or 3 to route your speech to different agents, APIs, or scripts.

• Command+1 → send to AI coding agent
• Command+2 → post to Slack channel
• Command+3 → create a task via API
• Default → paste at cursor as usual

✨

Text Transform

Process your speech before it arrives. Run it through a script, an LLM, or any command. The transformed text is what gets delivered.

• Remove filler words ("um", "like", "you know")
• Translate: speak Spanish → deliver English
• Prepend /start for agent commands
• Format as a social media post

🚀

Multiple Outputs

Text doesn't just go to your cursor. Send it to a webhook, log it to a file, pipe it to a script, or fire it at an API — all at once.

• paste — at cursor in any app
• exec — pipe to any script or CLI
• webhook — POST to any URL
• file — append to log for history

You say: "fix the auth bug in the login page, it's high priority"

↓ SpeechButton transcribes & transforms into a structured agent command:

/start-task fix auth bug in login page, priority: high

Config that makes it happen:

# Command+1: voice → structured task → send to AI agent
[[hotkey]]
key = "RightCommand"
channel = "1"
name = "agent-task"
transform = "python3 ~/scripts/to_task.py"      # speech → "/start-task ..." command

# Command+2: voice → clean text → paste at cursor
[[hotkey]]
key = "RightCommand"
channel = "2"
name = "clean-paste"
transform = "python3 ~/scripts/clean_filler.py"  # remove filler words

# Command+3: voice → create issue in Linear/GitHub
[[hotkey]]
key = "RightCommand"
channel = "3"
name = "create-issue"
transform = "python3 ~/scripts/format_issue.py"
exec = "bash ~/scripts/create_linear_issue.sh"

Built for Power Users

Hands-free agent workflows, voice-driven automation, and programmable text pipelines.

🗣

Hands-Free with VAD + Auto-Enter

Voice Activity Detection sends text as you speak. Combined with auto-Enter, you can talk to AI agents (Claude Code, ChatGPT, Slack bots) without touching the keyboard at all.

🛠

Text Config File

All settings in a single config.toml file. AI agents can configure SpeechButton programmatically — no GUI needed. Changes apply instantly without restart.

✨

Text Transform Pipeline

Process text before it's pasted: run it through a script, send it to an LLM API, or transform it locally. Get cleaned-up, formatted, or translated text — all from your voice.

🔌

Hotkey Channels

Hold Command, then press 1, 2, or 3 to route your speech to different destinations. Send voice to one agent, then switch to another with a different channel — perfect for multi-agent workflows.

🔗

Webhook & File Output

Send transcribed text to a webhook URL for integrations, or log everything to a file for history and audit. All outputs work simultaneously — paste, file, webhook, and exec at once.

📱

iPhone as Wireless Mic

Use your iPhone as an external microphone. With keep_hot = true the mic stays always-on — no 300ms wake-up delay when you start talking. Same blazing fast response, even over wireless.

{}

Text & JSON Output

Choose output_format = "text" for plain text or "json" for structured data with timestamps, language, and confidence — ideal for programmatic pipelines.

~/.config/speechbutton/config.toml

# Default: paste raw text at cursor
[[hotkey]]
key = "RightCommand"
name = "default"

# Command+1: clean filler words via Python before pasting
[[hotkey]]
key = "RightCommand"
channel = "1"
name = "ai-cleanup"
transform = "python3 ~/scripts/clean_filler.py"

# Command+2: translate to English via LLM API
[[hotkey]]
key = "RightCommand"
channel = "2"
name = "translate"
transform = "python3 ~/scripts/translate_en.py"

# Command+3: send to Slack via bash script
[[hotkey]]
key = "RightCommand"
channel = "3"
name = "slack-post"
exec = "bash ~/scripts/slack-post.sh"
output_format = "json"       # structured output with timestamps

# Output destinations (all work simultaneously)
[output]
paste = "accessibility"      # paste at cursor
file = "/tmp/speechbutton_log" # transcription history
webhook = "http://localhost:8080/transcription"

# Per-device settings (match by name)
[[device_rule]]
match = "iPhone"
keep_hot = true              # always-on mic → no 300ms wake delay

How It Works

Three steps. Zero configuration.

⏬

Step 1

Hold the Key

Press and hold Right Command (or your custom hotkey). The menu bar mic starts pulsing.

🗣

Step 2

Speak

Talk naturally in any supported language. Voice Activity Detection sends text as you talk.

✓

Step 3

Release

Let go of the key. Text is instantly pasted wherever your cursor is. Done.

Simple Pricing

Start free. Upgrade when you need more.

Free

$0

forever

✓ 15 min/day transcription
✓ All models & 25 languages
✓ 100% local & private
✓ Push-to-talk & VAD
✓ Auto-paste & auto-send

Download Free

Start Talking, Stop Typing

Download SpeechButton and get instant speech-to-text on your Mac. Free 15 minutes/day. Pro: unlimited.

 Download for macOS

Requires macOS 14 Sonoma or later · Apple Silicon (M1+)

├─	⌘	→	📝 Paste in active app
├─	⌘+1	→	🤖 Claude Code CEO Agent
├─	⌘+2	→	💬 Slack
└─	⌘+3	→	✅ Linear task

Blazing Fast Voice to Action Router

Why SpeechButton

100% Private & Local

25 Languages

7ms Instant Capture

AI-Ready Text Config

Talk to AI agents. Hands free.

Your Voice, Any Destination

Hotkey Channels

Text Transform

Multiple Outputs

Built for Power Users

Hands-Free with VAD + Auto-Enter

Text Config File

Text Transform Pipeline

Hotkey Channels

Webhook & File Output

iPhone as Wireless Mic

Text & JSON Output

How It Works

Hold the Key

Speak

Release

Simple Pricing

Start Talking, Stop Typing

Blazing Fast
Voice to Action Router

Talk to AI agents.
Hands free.