• Recent
  • Tags
  • Unsolved
  • Solved
  • MagicMirror² Repository
  • Documentation
  • 3rd-Party-Modules
  • Donate
  • Discord
  • Register
  • Login
MagicMirror Forum
  • Recent
  • Tags
  • Unsolved
  • Solved
  • MagicMirror² Repository
  • Documentation
  • 3rd-Party-Modules
  • Donate
  • Discord
  • Register
  • Login
A New Chapter for MagicMirror: The Community Takes the Lead
Read the statement by Michael Teeuw here.

MMM-OpenAI

Scheduled Pinned Locked Moved Productivity
24 Posts 4 Posters 9.3k Views 4 Watching
Loading More Posts
  • Oldest to Newest
  • Newest to Oldest
  • Most Votes
Reply
  • Reply as topic
Log in to reply
This topic has been deleted. Only users with topic management privileges can see it.
  • R Offline
    Rags @MMRIZE
    last edited by Rags Mar 7, 2023, 7:31 AM Mar 7, 2023, 6:57 AM

    @MMRIZE @MMRIZE
    Thanks for the update. Yes now it works fine. I am not getting "something is wrong’ messages, but prompts about the token lengths whenever they exceed.
    Thanks. I hope there will be voice integration soon.

    M R 2 Replies Last reply Mar 7, 2023, 8:35 AM Reply Quote 0
    • M Offline
      MMRIZE @Rags
      last edited by Mar 7, 2023, 8:35 AM

      @Rags
      I will not implement Voice-feature into this module directly by myself.
      But I believe other existing voice-related modules could be used together already.

      1 Reply Last reply Reply Quote 0
      • M Offline
        MMRIZE
        last edited by MMRIZE Mar 7, 2023, 7:30 PM Mar 7, 2023, 6:45 PM

        @Rags
        Speech example: Conjunction with MMM-GoogleTTS, now it can speak.

        https://youtu.be/daWuSfQc5Ns

        postProcessing: (helper, resp) => {
          let choice = resp.response?.choices[0]
          if (choice) helper.sendNotification('TTS_SAY', choice?.message?.content ?? choice?.text)
        }
        
        S R 2 Replies Last reply Mar 7, 2023, 7:00 PM Reply Quote 0
        • S Offline
          sdmydbr9 @MMRIZE
          last edited by Mar 7, 2023, 7:00 PM

          @MMRIZE a similar idea has crossed my mind. Using a Hotword detector like the one used in google assignment module to activate a listener for voice and ask for voice input and then using the input provided, get the transcript of the audio using the whisper api or something similar to get the transcript… pass on the transcript as a content in the OPENAI_REQUEST notification and then SHOW_ALERT or just read it out loud using the MMM-GoogleTTS. Just a rough sketch. I’m sure someone out here will come up with more convincing and better ideas.

          S M 2 Replies Last reply Mar 7, 2023, 8:51 PM Reply Quote -1
          • S Away
            sdetweil @sdmydbr9
            last edited by Mar 7, 2023, 8:51 PM

            @sdmydbr9 use a GoogleAssistant recipe

            see it’s recipies folder

            Sam

            How to add modules

            learning how to use browser developers window for css changes

            S 1 Reply Last reply Mar 8, 2023, 3:04 AM Reply Quote 0
            • M Offline
              MMRIZE @sdmydbr9
              last edited by MMRIZE Mar 7, 2023, 9:18 PM Mar 7, 2023, 9:15 PM

              @sdmydbr9
              I have a few already, like MMM-Hotword or MMM-Clap, and some…

              Anyway new OpenAI’s Whisper looks so interesting, So I’ll make it as a STT module in a few days, hope so.

              S 1 Reply Last reply Mar 8, 2023, 3:10 AM Reply Quote 0
              • S Offline
                sdmydbr9 @sdetweil
                last edited by Mar 8, 2023, 3:04 AM

                @sdetweil I just meant it as a similar approach, I don’t actually want to implement the whole assistant module.

                1 Reply Last reply Reply Quote 0
                • S Offline
                  sdmydbr9 @MMRIZE
                  last edited by Mar 8, 2023, 3:10 AM

                  @MMRIZE I think the Hotword module is not Available anymore and the clap module, might work but it will not look as asthetic as activating with the hot word…

                  1 Reply Last reply Reply Quote 0
                  • R Offline
                    Rags @MMRIZE
                    last edited by Mar 11, 2023, 8:41 AM

                    @MMRIZE said in MMM-OpenAI:

                    @Rags
                    Speech example: Conjunction with MMM-GoogleTTS, now it can speak.

                    https://youtu.be/daWuSfQc5Ns

                    postProcessing: (helper, resp) => {
                      let choice = resp.response?.choices[0]
                      if (choice) helper.sendNotification('TTS_SAY', choice?.message?.content ?? choice?.text)
                    }
                    

                    I am getting a syntax error in these lines can you please check.
                    Thanks

                    R 1 Reply Last reply Mar 12, 2023, 4:34 AM Reply Quote 0
                    • R Offline
                      Rags @Rags
                      last edited by Rags Mar 12, 2023, 4:36 AM Mar 12, 2023, 4:34 AM

                      @MMRIZE
                      It’s possible that the error is caused by using optional chaining in a JavaScript version that doesn’t support it.

                      I modified the code as below, rewriting the code without using optional chaining.
                      postProcessing: function(helper, resp) {
                      let choice = resp.response ? resp.response.choices[0] : undefined;
                      if (choice) {
                      let message = choice.message ? choice.message.content.choice.text : undefined;
                      if (message) {
                      helper.sendNotification(‘TTS_SAY’, message);
                      }
                      }

                      I am not getting any syntax error now. However, there is some issue with Google TTS (unrelated I think) , as it is sending a notification as TTS_Say_Error. Google TTS API hopefully is configured correctly as no errors are thrown up during starting MM. How should i go about resolving it.

                      M 2 Replies Last reply Mar 12, 2023, 11:30 AM Reply Quote 0
                      • 1
                      • 2
                      • 3
                      • 2 / 3
                      2 / 3
                      • First post
                        11/24
                        Last post
                      Enjoying MagicMirror? Please consider a donation!
                      MagicMirror created by Michael Teeuw.
                      Forum managed by Sam, technical setup by Karsten.
                      This forum is using NodeBB as its core | Contributors
                      Contact | Privacy Policy