Menu
Convert text to speech with ElevenLabs voiceover. Use when generating speech audio or browsing available voices.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Iteratively improve a feinschliff diagram skill: loop measure, mutate one thing, keep or revert, consolidate, scoring generated output with `feinschliff-builder eval`. Rides the built-in /goal. Use when asked to autoloop against its evals.
Use when a brand pack scaffold exists and you need to close the structural fidelity gap against a source PPTX — runs the verify-loop, then fans out one sub-agent per layout above threshold so each slide is analysed and edited in parallel.
Use when authoring a CLI session recording for the cli-recorder skill. Translates a user's intent ("video of installing kubectl") into a valid recipe.toml through interactive Q&A.
Generate Excalidraw diagrams from a compact DSL with brand-resolved colors. Use for boxes/arrows flow diagrams.
Generate SVG diagrams from a compact DSL with brand-resolved colors. Use for charts, flows, and schematic 2D graphics.
Scaffold v2 `.slide.dsl` layout skeletons for a brand pack from its claude-design HTML. Use when adding new layouts.
| name | tts |
| description | Convert text to speech with ElevenLabs voiceover. Use when generating speech audio or browsing available voices. |
feinklang is a command on your PATH — no file paths, no cd, no
${CLAUDE_PLUGIN_ROOT}. Requires ELEVENLABS_API_KEY (an export, or a line in
~/.env). Default voice: Hale.
feinklang tts --text "Hello, this is a test." --out voiceover.mp3
Options:
--voice-id — voice ID or name (Hale, Mike, Lea), default Hale--model-id — eleven_multilingual_v2 (default), eleven_v3, eleven_flash_v2_5--format — mp3_44100_128 (default), mp3_44100_192, wav_44100, pcm_44100, opus_48000_64--stability — 0–1 (default 0.5)--similarity-boost — 0–1 (default 0.75)--speed — 0.7–1.2 (default 1.0)--play — play the audio locally after generation--out — output path; if omitted, a timestamped file is written to the temp
dir and its path is printedWrite outputs into the project (e.g. a beats directory under
${CLAUDE_PROJECT_DIR}) so downstream plugins can consume them.
feinklang voices # all voices
feinklang voices --category professional # cloned | professional | premade
feinklang voices --search Mike # search by name
Need a voiceover? Call feinklang tts --text "…" --out <project-path> as a
bare command and read the resulting file — for example, loop it per beat to
batch-generate narration. Do not reference feinklang's internal files; the
CLI is the entire contract. If feinklang is somehow not on PATH, fall back to
asking the user for the audio rather than failing hard.