Buildship Meditation GPT
Hello. My name is Jason. I am trying to learn and use Buildship to Flutterflow to build a voice-first/chat assistant that combines various somatic wellness techniques to create routines to help be enhance their wellness. Coming from a background in web design and digital marketing, as well as having a certification in breathwork, I wanted to come up with something that would combine my many skills and interests. I have for the most part been enthusiastic about learning new skills and tools.
I got as far as planning and developing the concept and UI in Flutterflow. I'm finally starting to get my head around how to build the front-end in Flutterflow and connecting it all together. Where I am struggling most is in Buildship.
It took me a month, but I finally, after much persistence, figured out how to get how to get streaming chat to work. Now I am trying to tackle the next level in my Buildship learning... the Meditation GPT template.
Initially, started to set it up with an ElevenLabs voice I found, and liked very much, but as I ran into a snag in testing, I watched as my character count (each test) dwindled down by 1000. I saw in the logs that the text-speech was working, but where it's not is in the "Combine Audio" node, I am consistently getting a "FFmpeg exited with code 1" error and I have no idea why. I copied the template from the Template library, and followed the video on YouTube, step-by-step.
Though, I did change the text-to-speech from ElevenLabs to Open AI's tts-1-hd...
One thing I noticed is that in the video it shows a JSON Parse node, but that node isn't in the template. The video and the template do not seem to be one-to-one...
I've been slow to reach out and ask anyone for help, trying to read the documentation, watch the videos, and learn on my own. I used to think I was a pretty smart guy and could figure these things out. Now I'm not so sure anymore. lol
If anyone could offer some support, I would be most grateful. Thank you, Jason
I got as far as planning and developing the concept and UI in Flutterflow. I'm finally starting to get my head around how to build the front-end in Flutterflow and connecting it all together. Where I am struggling most is in Buildship.
It took me a month, but I finally, after much persistence, figured out how to get how to get streaming chat to work. Now I am trying to tackle the next level in my Buildship learning... the Meditation GPT template.
Initially, started to set it up with an ElevenLabs voice I found, and liked very much, but as I ran into a snag in testing, I watched as my character count (each test) dwindled down by 1000. I saw in the logs that the text-speech was working, but where it's not is in the "Combine Audio" node, I am consistently getting a "FFmpeg exited with code 1" error and I have no idea why. I copied the template from the Template library, and followed the video on YouTube, step-by-step.
Though, I did change the text-to-speech from ElevenLabs to Open AI's tts-1-hd...
One thing I noticed is that in the video it shows a JSON Parse node, but that node isn't in the template. The video and the template do not seem to be one-to-one...
I've been slow to reach out and ask anyone for help, trying to read the documentation, watch the videos, and learn on my own. I used to think I was a pretty smart guy and could figure these things out. Now I'm not so sure anymore. lol
If anyone could offer some support, I would be most grateful. Thank you, Jason
Solution
Hi @Jason Samadhi, Sent you an email with cause of the issue and solution, you can reply all to the email for any further questions.
Also, sharing the reply here - Regarding the error "FFmpeg exited with code 1" on the combine audio node, on taking a look at your modified workflow (iffvISDRGkXPfXo56kyk), you have switched the playHT node with OpenAI Text-to-Speech node, which is causing the issue here. Elaborating the issue and the solution below:
Issue - The OpenAI Text to Speech node returns a base64 instead of URL whereas the combine audio node only accepts an array of URL as input in the audio file path.
Solution - Using any other text-to-speech node that return a URL should fix the issue. For example, I used Eleven Labs text-to-speech node and the new combine FFmpeg node from the FFmpeg integration, which worked perfectly fine.
For your reference and ease, I've created a modified working and tested workflow for Meditate GPT which you can clone and use by adding your api-keys/secrets. Also attaching a test screenshot and a remix link of the workflow.
Remix Link - https://buildship.app/remix/1166d4de-cc43-494b-84f4-fdafd6f031d4.
Hope this helps and keeps you going with BuildShip.
Also, sharing the reply here - Regarding the error "FFmpeg exited with code 1" on the combine audio node, on taking a look at your modified workflow (iffvISDRGkXPfXo56kyk), you have switched the playHT node with OpenAI Text-to-Speech node, which is causing the issue here. Elaborating the issue and the solution below:
Issue - The OpenAI Text to Speech node returns a base64 instead of URL whereas the combine audio node only accepts an array of URL as input in the audio file path.
Solution - Using any other text-to-speech node that return a URL should fix the issue. For example, I used Eleven Labs text-to-speech node and the new combine FFmpeg node from the FFmpeg integration, which worked perfectly fine.
For your reference and ease, I've created a modified working and tested workflow for Meditate GPT which you can clone and use by adding your api-keys/secrets. Also attaching a test screenshot and a remix link of the workflow.
Remix Link - https://buildship.app/remix/1166d4de-cc43-494b-84f4-fdafd6f031d4.
Hope this helps and keeps you going with BuildShip.
Visually build workflows and powerful backend logic for your apps. Powered by AI, connect to anything with or without code.
