Hey lemmy!

I was wondering if anyone was interested in checking out an AI radio app that I’ve put together.

Really just looking for feedback and overall impressions. Obviously if it’s against the rules (I didnt see a rule this would violate), I wont post the link. If you guys are interested, I’ll edit the post to include the link.

Thanks guys!

EDIT: as @db2 mentions, I didnt describe what the app actually does… It’s an AI radio app with various stations that all play back AI generated music. All different genres. Everything but lyrics is generated locally (I need to experiment with some local models to see which produce lyrics well)

  • SuspciousCarrot78English
    2·
    2 days ago

    Do it :) It would add a lot, I think. Though it introduces some complexity on your end if you have to geo-tag canonical feeds per user, per each location, to extract from; a few set ones (technology, science, world news etc) per each station might be easier…but then have the DJ announce in the voice of whatever that IP address is from?

    Dunno. You’re clearly more than capable of working it out, so I look forward to seeing what you do.

    • doodlebobOPEnglish
      2·
      2 days ago

      OK so, I’m almost done with the tool for the AI DJ. Basically we’re using searxng to search for audience locale news + using rss feeds to provide the llm with context about specific news categories (Technology for example)

        • doodlebobOPEnglish
          1·
          2 days ago

          You can definitely give it a shot now, it’s done at this point! Keep in mind the llm can pick and choose between the various tools to call so news may not be called out each time

          • SuspciousCarrot78English
            2·
            1 day ago

            Nice :) I have it on right now. Might need a touch more reverb, though that could just be the track (“Silence Between Thunder and Lightning”). Definitely in the ballpark. Cheers for that.

            I had an idea for you driving home, though it may introduce scope creep.

            Have you considered a hybrid station mode where the user can supply their own music library and Synapse FM intermingles it with the generated tracks? For example, maybe the user uploads a playlist manifest plus files or points Synapse at a Google Drive / Dropbox folder containing MP3s and an .m3u playlist. Then the system could:

            • randomly select from the user’s own tracks
            • blend them into the generated station flow
            • use metadata / embeddings / simple tagging to keep tonal consistency
            • optionally let the AI DJ introduce those tracks as part of the same station identity

            So instead of pure AI radio, it becomes something closer to:

            “your own music taste, extended infinitely”

            That feels like a pretty compelling hook to me…and might actually protect your from the haters.

            Set it up so tracks are either played directly, or used as “station DNA” for selection / matching / transitions. Or both.

            Or (and this is my preference) you could have it so that the scheduler inserts user tracks every N songs.

            You could even allow users to tip the balance, user side:

            • AI only
            • Mostly AI
            • Balanced
            • Mostly my library

            I’m handwaving away a lot here but even as a local/private beta feature for you alone, it seems like a genuinely interesting direction.

            Again - scope creep / you might see it differently than I do. Still, even if you just play with it at home, try it and see if the idea works,

            Just wanted to share, one journeyman to another.

            It’s a good project and you SHOULD post the URL here (I won’t / am respecting your privacy).

            Be proud of it, it’s good work.

            EDIT: Just caught the jingle between songs - well done! Exactly right.