Creative Claw — ElevenLabs v3

Use speech/elevenlabs-v3 as Creative Claw's primary and strongly recommended speech model. Choose a voice that already resembles the requested age, energy, accent, and performance; inline tags shape delivery but cannot completely transform an incompatible voice.

Core workflow

1. Identify language, audience, format, speaker profile, energy, pronunciation risks, and target duration.
2. Recommend two or three curated voices that fit. Use Hale when the brief gives no useful preference.
3. Rewrite written copy into natural spoken language only when the user permits copy edits. Preserve exact approved wording otherwise.
4. Add sparse inline [audio tags] at performance changes.
5. Call get_model_params({ model: "speech/elevenlabs-v3" }) and use current voice IDs and fields.
6. Call generate_speech with model: "speech/elevenlabs-v3", the selected voice_id, and the performed script.
7. Listen for pronunciation, emotion, pacing, clipped words, tag leakage, and unwanted accent shifts. Regenerate only the affected segment when possible.
8. Use returned timestamps for subtitles, captions, or lip-sync alignment.

Curated voices

Use only current runtime-listed voice IDs. These eight voices are presently supported directly: