Automate PR0TA audio production with ElevenLabs v3 TTS and Scribe V2 transcription.
npx skills add https://github.com/jeffamerican/pr0ta-plugin --skill pr0ta-audio
Please help me install this Agent Skill. Skill: pr0ta-audio Source: https://github.com/jeffamerican/pr0ta-plugin/tree/main/skills/pr0ta-audio Command: npx skills add https://github.com/jeffamerican/pr0ta-plugin --skill pr0ta-audio
PR0TA audio generation and transcription streamlines end-to-end voice work: TTS, voice cloning, design prompts, STS, and transcription for storytelling in PR0TA productions.
Generate a short narration using ElevenLabs v3, then transcribe it with Scribe V2 to populate the narration timeline.
High-intent search queries and answers about installing and using this skill.
Generate narration using ElevenLabs v3 text-to-speech, then transcribe the output with Scribe V2 to extract word-level timing and speaker diarization for populating a narration timeline.
Voice cloning and speech-to-speech transformation adapt performances to new voices while preserving original timing and emotion, enabling consistent character dialogue across different voice personas.
Word-level transcription with diarization tags individual speakers and timestamps each word, needed when aligning character dialogue or narration events to a precise production timeline.
API-driven generation supports multilingual voice output and model selection, allowing you to choose specific TTS models and generate audio across multiple languages for diverse project requirements.
Use voice design prompts to craft distinct voice personas for consistent on-brand narration, defining specific vocal characteristics that remain uniform across generated dialogue and storytelling scenes.
Combine ElevenLabs v3 for text-to-speech generation, apply voice cloning or STS for performance adaptation, and run Scribe V2 transcription to assemble word-level timing data into a final narration timeline.
storyclaw-officialTranscribe audio files into text using ElevenLabs Scribe v2.
47thtechcornerGenerate Mandarin and multilingual audio narration with word-level timing metadata via the Volcengine Doubao Speech 2.0 API.
0xslineAutomate ASR transcription, captioning, and subtitle management for video and audio assets.
shige1014-devTranscribe audio files into timestamped text with word-level timing.
