Say

malob/nix-config

Converts Claude's text responses into spoken audio at your preferred pace, defaulting to 300 words per minute. You'd reach for this when you want to listen to responses instead of reading them, maybe while stepping away from your keyboard or during long explanations you'd rather absorb audibly. It's a simple bash wrapper around text-to-speech that grabs the last thing Claude said and pipes it through your system's TTS engine. The rate parameter is genuinely useful since 300 WPM is pretty quick, so you might dial it down to 200 or so for dense technical content. Nothing fancy here, just a straightforward utility that does one thing without overthinking it.

GitHub stars

460

last updated

Jun 7, 2026

${CLAUDE_PLUGIN_ROOT}/skills/say/scripts/speak.sh ${CLAUDE_SESSION_ID} $1

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Recommended

1cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs

2grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs

3improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs

4systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs

5karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs

6find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs