Matthew - So I am retreving Text to speech base...
So I am retreving Text to speech base 64 from openai, but i need to put that into an audio file, so my users can hear it any idea on how to do this?
9 Replies
Hi @Matthew, you can generate a node with AI to convert base64 to audio, here's a workflow remix you can clone and directly use, it converts speech base64 from openai to audio file and uploads to GCP. https://buildship.app/remix/c53aa870-6bd7-4f86-a557-5b91a5d55026
got it! Just hate how the OpenAI node take so long
It depends on your content length, the above shared workflow takes ~4 seconds, feel free to clone.
im having issues with the groq speeceh to text though, its asking for the audio file path, have no idea where to get this since the audio is coming from firestore data
You can modify the convert base64 to audio node with AI to return a path instead of url then pass the pah to the groq node, leveraging AI feature should help you overcome these challenges.
when i use the remix you gave me it ooutputs this file but wont let me play the audio
You can check if you have provide text and the base64 generated by open AI is valid, this usually occurs when the openai credits are exhausted and a blank base64 is generated.
yeah everything is populating as it should
just getting that issue above
If im wainting to add a deepgram node using the AI generation feature. How do you represent going about setting that up
Yeah, you should be able to create one with their API or SDK, you can watch this tutorial to generate one with AI https://www.youtube.com/watch?v=AawYfYW8xu0.
BuildShip
YouTube
Generating Custom Nodes with AI - BuildShip AI Workflow Builder
Get started with BuildShip for FREE 👉 https://buildship.com
A Low-code Visual Backend Builder with AI
💬 Chat and build together with a community of no-code/low-code developers: https://buildship.com/discord
🐦 Tweets: https://twitter.com/buildshipapp
#nocode #backend #apibuilder #lowcode #cronjob #scheduledtask #backgroundjob #googlecloud #ope...