Hi Chakor, may I request a specific tutorial on how to build a 'Speech-to-text' bubble app for the future videos? really interested to learn about the API integration part too. Thanks again!
Love the way you simplify things brother. I have tried the whisperer in Google collab bit its too slow, is it sane with API in bubble? Also, can we also have the transcript after translating the audio into English
Glad you liked the tutorial. Whisperer is faster in Bubble as you can see in the video. However GPT-4 models cause timeout issues in API connector but Bubble is already working on resolving this issue. For creating a transcript, we are working to include this in our OpenAI plugin but for now you can use integrate this API from API connector: platform.openai.com/docs/api-reference/audio/create
@@thechakor okay thanks, but are you not anyway getting the string from audio convert and then sending string value to elevenlabs. So can we just also forward the same output string to display?
Hey, I am explaining Text To Speech functionality at 4:33 in the video. You can use this ElevenLabs plugin Bubble io: bubble.io/plugin/text-to-speech-elevenlabs-1679044060622x772568185710575600 Working of this plugin is explained here: forum.bubble.io/t/how-to-convert-text-to-speech-via-eleven-labs-api/252558
Great video! Thank you!
How would we be able to auto-play the Howler A file as soon as it has been uploaded? Without clicking anything.
Hi Chakor, may I request a specific tutorial on how to build a 'Speech-to-text' bubble app for the future videos?
really interested to learn about the API integration part too.
Thanks again!
Hey! Great Video. Quick question, do you know why I'm not able to select 'Clear Audiorecorder A' from the actions?
Thank you so much!
Love the way you simplify things brother. I have tried the whisperer in Google collab bit its too slow, is it sane with API in bubble? Also, can we also have the transcript after translating the audio into English
Glad you liked the tutorial. Whisperer is faster in Bubble as you can see in the video. However GPT-4 models cause timeout issues in API connector but Bubble is already working on resolving this issue.
For creating a transcript, we are working to include this in our OpenAI plugin but for now you can use integrate this API from API connector: platform.openai.com/docs/api-reference/audio/create
@@thechakor okay thanks, but are you not anyway getting the string from audio convert and then sending string value to elevenlabs. So can we just also forward the same output string to display?
Can u make a vid how to use the text2speach Funktion of elevenlabs in bubble ?
Hey, I am explaining Text To Speech functionality at 4:33 in the video.
You can use this ElevenLabs plugin Bubble io:
bubble.io/plugin/text-to-speech-elevenlabs-1679044060622x772568185710575600
Working of this plugin is explained here:
forum.bubble.io/t/how-to-convert-text-to-speech-via-eleven-labs-api/252558
Hey I emailed you we had that call early this morning
Awesome. We'll come back to you soon!
very poor way of explaining!
Thank you for the feedback. Can you please add some instructions which can help us explain in a better way?