Platforms
AUDIOAI
Audio generation + transcription.
All audio Mat owns, in one brain — TTS generation, Whisper transcripts, podcast outputs, daily journal recordings, AAD pipelines, master index.
- TTS routing across Voxtral · ElevenLabs · OpenAI · local with voice persona mapping
- Whisper VTT transcripts for every file — every minute fully searchable
- AAD daily cron publishes spoken PAD and LAD on schedule
- Podcast-ready RSS feed and searchable archive for the full catalogue
Why
Audio is the most underserved modality in most AI production pipelines. AUDIOAI gives the fleet a single audio brain — TTS generation, transcription, and a searchable archive — so every text output gets a spoken version for free.
How
- TTS generation with provider routing and voice persona mapping per output type
- Whisper VTT transcripts for every file — searchable in full, captionable
- AAD cron publishes daily; podcast-ready RSS feed auto-updates the archive
Proof
- Hours archived
- 200+
- TTS providers
- Voxtral · ElevenLabs · OpenAI · local
- Searchable index
- every minute
In production
- 200+ hours archived
TTS catalogue spanning PAD, LAD, podcast feeds — every minute Whisper-transcribed and searchable.
- Four-provider TTS router
Voxtral, ElevenLabs, OpenAI, local — routed by content type and voice persona.
- Podcast-ready RSS
Auto-updating RSS feed turns the catalogue into a podcast — same content, different surface.