Audio Intelligence in Preemptive AI for Domino automates transcription and optional translation of audio, then structures and summarizes the results with custom LLM prompts. It orchestrates:
- Ingestion of audio files or recordings
- Transcription via OpenAI’s Whisper ASR
- Optional translation to English
- Post-processing with Domino-driven LLM prompts (e.g., summaries, action items, formatting)
This delivers consistent, searchable text and structured insights from spoken content directly from your inbox.
Audio Intelligence is implemented as a set of tasks with the Preemptive AI-Proxy database. It uses the advanced Whisper ASR from OpenAI for audio transcription.
The user emails an mp3 or wav file to the AI-Request database, a request is created, and then the AI-Proxy database processes it. Finally, an email is returned with the transcribed text, along with summary information.
Click here for more information on Whisper
Click here for our Audio Intelligence Quick Start Guide.