oma-voice

1# Voice Skill - Speech and Local Audio Processing
2 
3## Scheduling
4 
5### Goal
6Generate and transcribe speech through a local speech backend (the Voicebox app, or VoiceStudio per `voice.backend`), and process existing audio with local media tools. The backend owns synthesis engines and profiles; FFmpeg owns file conversion, duration adjustment, and loudness processing.
7 
8### Intent signature
9- User asks to generate speech, narrate text, produce a voiceover, create an mp3 or wav from text.
10- User wants an audio file transcribed into text, meeting notes, or a transcript.
11- User asks for a voice notification when a long task completes or a workflow step is blocked.
12- Another skill needs local audio generation infrastructure.
13- User needs existing speech fitted to a time window, resampled, converted, or loudness-normalized.
14 
15### When to use
16- Generating short notification audio for agent task completion or blockers.
17- Producing voiceover, narration, or audio assets (mp3 or wav) for apps and content.
18- Transcribing local audio files (mp3, wav, m4a, webm, flac) to Markdown.
19- Comparing voice profiles by re-running the same text against different profile ids.
20- Processing an existing audio asset, including speech used in an `oma-video` dubbing job.
21 
22### When NOT to use
23- Cloud TTS or high-fidelity multilingual cloud voices -> out of scope; future multi-vendor extension.
24- Real-time microphone dictation loop in the terminal -> use Voicebox app's built-in hotkey dictation.
25…