All 94 skillsDesign and media8 of 10

stryx:audio

When AI must speak, transcribe or make music: voiceovers, subtitles, sound effects.

/stryx:audio

Inside its piece: 13 specks, one for each file on its shelf. Its nine group-mates glow on the open book behind it. The light splits toward yellow, the band of Design and media.

In numbers

counted 2026-10-12 in the installed set
  • 9reference files
  • 2helper scripts
  • 13files in the skill
  • 145KB on disk
  • 8chapters

Use it when

in the skill’s own words

When generating or transcribing audio with AI

    • text-to-speech
    • voiceovers
    • narration
    • audiobooks
    • multi-speaker dialogue
    • voice settings
    • audio tags
    • pronunciation
    • long-text stitching
    • speech streaming over HTTP or WebSocket
    • phone (μ-law) audio or instant voice clones on ElevenLabs
    • speech-to-text
    • transcripts
    • subtitles or SRT
    • meetings with speaker labels
    • keyterms
    • PII redaction
    • live microphone transcription (Scribe v2 and Realtime, single-use tokens, useScribe) or offline transcription on the local GPU with Whisper
  • AI music, jingles, background tracks or songs with lyrics (Eleven Music, composition plans)
  • Sound effects, ambiences, UI sounds or loops
  • ElevenLabs SDK setup, the deprecated "elevenlabs" npm package and 401/422/429 errors

Not for

another skill does it

On its shelf

13 files, 145 KB
  • references/9
  • scripts/2
  • SKILL.md1
  • evals/1

Inside the book

8 chapters, by title only
  1. Every task: the procedure
  2. Pick the engine and model
  3. Rules
  4. Old way vs current way
  5. Failure modes: signs and fixes
  6. Verification: what a pass looks like
  7. Worked examples
  8. Local models: one door

Works with

the skills it names most

Claude loads it by itself when the moment comes; by hand, type the line at the top. It comes with the whole set: Installs all 94 skills, 32 agents and the brain program as one set. The skill’s own text is private source and is not shown here.