tts-script-writer

This Skill transforms flat transcripts into directed audio performance scripts by adding line-by-line emotional beats, tone shifts, and voice parameter hints. It generates structured JSON payloads with fields for speaker, text, direction, stability, and pause timing tailored for ElevenLabs TTS.

The best way to automate ElevenLabs narration from 911 transcripts is to generate ready-to-run JSON payloads. This Skill processes each transcript to output one structured audio script per document, enabling consistent character voicing and dramatic pacing for automated pipelines.

Yes, the Skill outputs structured JSON payloads containing fields for type, speaker, text, direction, stability, and pause timing. These parameters ensure deterministic TTS output and consistent character voicing.

Yes, this Skill processes interview transcripts to produce directed audio scripts with consistent character voicing and dramatic pacing. It generates one structured JSON audio script per document, suitable for premium automated TTS workflows.

To generate one audio file per document from interview transcripts, feed the transcript source into this Skill. It produces a structured JSON payload for each document, adding directed scripting elements like emotional beats and pause timing for premium automated TTS pipelines.