speak
Skill0 starsChanged 2 months agoMITView on GitHub
Toggle spoken replies. /speak (toggle) · /speak on · /speak off · /speak mute (mute THIS session only) · /speak unmute · /speak muted (list) · /speak again (re-read the last reply) · /speak stop · /speak rate 180 · /speak voice Samantha. When on, every finished reply is read aloud via macOS `say`.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- revagomes/kiro-power-narratetheir own version, first seen Nov 8, 2026
- bas1l/claude-skillstheir own version, first seen Nov 3, 2026
- rahulrajaram/rahulskillstheir own version, first seen Oct 13, 2026
- Vachilla64/speak-skilltheir own version, first seen Oct 13, 2026
- babysor/MockingBirdtheir own version, first seen Oct 8, 2026
- jjeff/herdr-speaktheir own version, first seen Oct 8, 2026
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- babysor/MockingBird★ 37ksame name
- blacktop/mcp-tts★ 74same name
- jpboliv/eridian★ 20same name
- MichaelPGifford/claude-read-aloud★ 10same name
- popmechanic/Julian★ 9same name
- tomo3141592653/ayumu-oss★ 9same name
- alamparelli/mcp-claude-say★ 8same name
- revagomes/kiro-power-narrate★ 4same name
- silverdolphin863/claude-speak★ 4same name
- haraGADygyl/claude-speak★ 1same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
- talkSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Run exactly one shell command and report its one-line output, nothing else:
- Very specific: line 9
If $ARGUMENTS is empty, run ~/bin/talk-speak speak toggle.
- Distinctive: line 16
Do not add commentary beyond the command's output line (the line itself will be spoken if speech is on).
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run exactly one shell command and report its one-line output, nothing else:
~/bin/talk-speak speak $ARGUMENTS
If $ARGUMENTS is empty, run ~/bin/talk-speak speak toggle.
Scoped mutes (global speech stays ON, only the target goes quiet):
/speak muteor/speak unmutewith no id: supply THIS session's id yourself. It is the UUID path component before/scratchpadin your scratchpad directory (e.g..../<session-uuid>/scratchpad). Run~/bin/talk-speak speak mute <session-uuid>.- With an explicit id (
/speak mute <uuid>), pass it through as-is. - Headless runners (LaunchAgents calling
claude -p) are silenced withTALK_SPEAK=off(orCLAUDE_SPEAK=off) in the environment of the call, not with mute.
Do not add commentary beyond the command's output line (the line itself will be spoken if speech is on).
How it works: the Claude Code Stop hook (~/.talk-speak/bin/speak-last.sh) extracts the last reply from the transcript and pipes it to the shared engine ~/.talk-speak/bin/speak-text.sh, which owns the on/off flag, rate, voice, last-reply.txt and replay protection. Other harnesses feed the same engine through the adapters in the talk-speak repo (speak/adapters/), so /speak on|off|rate|voice|again govern all of them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.