Drag the background!
World: Generate Images from Audio

Owner: Toma  
API: Webpage (r2)
World type: No Mind

Audio (record microphone speech) to text to image. (1) Enable microphone for Ancient Brain. (Maybe disable after.) Audio recorded using MediaStream Recording API: https://developer.mozilla.org/en-US/docs/Web/API/MediaStream_Recording_API. (2) Click "Use Audio" to send audio to OpenAI Whisper transcription service. Need to enter your own OpenAI API key. OpenAI returns transcript of audio. (3) Send transcript to OpenAI DALL-E to generate image. DALL-E generates images on a server and web page can include them directly. Author: Toma Emoghene-Ijatomi.

Created: 12 Nov 2023
Modified: 11 Sep 2024

Type: Public. Plain JS.
View plain JS.

Get Embed code.
Get New window embed code.
Get Autorun embed code.

155 runs

Tweet this World:  

Run
Edit Must be logged in.
Update image Must be logged in.
Clone Must be logged in.
New Mind Only valid for Worlds that use Minds.
Change World type Must be owner.
Change API Must be owner.
Delete Must be owner.
The background is a program, showing the JavaScript graphics used on this site.
The globes light up when you log in.
 
Font:

Users retain ownership of user content.

Platforms      Stats      The name      Terms and conditions

Call for partners      Contact

Call for partners!
Ancient Brain is looking for a partner to co-write a JavaScript coding book for schools, to be used worldwide. This would be a course for students in learning to code from scratch. The book and course will be integrated into the Ancient Brain site. This is an opportunity for someone looking to develop a course and textbook to partner with a site to promote it. Read more.