Jacques B Posted January 31 Report Share Posted January 31 It would be great if Intella Connect implemented something like Faster Whisper (https://github.com/SYSTRAN/faster-whisper) to automatically transcribe audio from audio and video files and index the transcribed content within the case. A counterpart said they are using it with Nuix where Nuix uses its API to reach out to Faster Whisper they have set up to transcribe, and feed it back to Nuix. Intella could one up them by doing it all seamlessly by allowing us to point to a Whisper server similar to pointing to Node :). Or incorporate it directly into Intella so we don't have to set up our own instance of Whisper and make sure it's properly configured. Quote Link to comment Share on other sites More sharing options...
Guest Marco de Moulin Posted February 1 Report Share Posted February 1 Hi @Jacques B, Thank you for this suggestion! We have many good ideas in this area and that he can expect more from Intella in the future regarding AI. How that integration is going to look like is something I cannot comment on at the moment. As a workaround compatible with your current version, you can export a selection of audio files to a new case and run a crawler script on it to transcribe the content into separate files. The crawler script can call a local instance (faster-whisper) or an API endpoint from OpenAI. Marco Quote Link to comment Share on other sites More sharing options...
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.