Raevenlord
News Editor
- Joined
- Aug 12, 2016
- Messages
- 3,755 (1.33/day)
- Location
- Portugal
| System Name | The Ryzening |
|---|---|
| Processor | AMD Ryzen 9 5900X |
| Motherboard | MSI X570 MAG TOMAHAWK |
| Cooling | Lian Li Galahad 360mm AIO |
| Memory | 32 GB G.Skill Trident Z F4-3733 (4x 8 GB) |
| Video Card(s) | Gigabyte RTX 3070 Ti |
| Storage | Boot: Transcend MTE220S 2TB, Kintson A2000 1TB, Seagate Firewolf Pro 14 TB |
| Display(s) | Acer Nitro VG270UP (1440p 144 Hz IPS) |
| Case | Lian Li O11DX Dynamic White |
| Audio Device(s) | iFi Audio Zen DAC |
| Power Supply | Seasonic Focus+ 750 W |
| Mouse | Cooler Master Masterkeys Lite L |
| Keyboard | Cooler Master Masterkeys Lite L |
| Software | Windows 10 x64 |
Hey guys. I'd like to use the brains of TPU's Forums for a personal project.
The basic idea is this: I write poetry, and I usually go to poetry readings, and all of that. And I found myself thinking on how every poetry read is different, even if everything stays the same. This comes from differences in tone, highs, lows, pauses, in-breaths, and all of those usual speech-related details. Even more so, obviously, if the reader is different.
This got me thinking: is there a way I could use a recording/an audio file to generate an image? The diagram is simple.
Record > Output audio file > Import audio file to an application > the application reads the audio, analyzes frequencies, and uses that to generate an image based on a preset algorithm (if it allows for variable changes when it comes to the image's creation, that would be best) > output. Of course, one could also just analyze the audio and export it in some automated way into text, which is then used as the input for a program that creates the image from it.
I know there are some random fractal generators that create images based on a pretty basic algorithm. I'm thinking something like that, but not fractal-based. I don't know what - if anything - is out there in this regard.
I looked a bit into some AI-based GAANs and all of that, ML-based animations, such as GANBreeder, but I haven't found anything that can generate an imagetic output from an audio input.
I liked the concept from this music visualization work, and this random walkers tutorial which seems like it could create something I like. I also really enjoyed the creations from this generative art tutorial.
I feel like this post is somehow all over the place, but I hope you get the gist of it. Sometimes it's hard to focus with all these ideas swirling around, so, thanks for reading.
TL;DR: I want to create images, perhaps like the one on top, from audio files. How?
PS: I have zero coding skills, so I'd be looking at mix and matching different apps, if needed, to achieve the desired effect.
The basic idea is this: I write poetry, and I usually go to poetry readings, and all of that. And I found myself thinking on how every poetry read is different, even if everything stays the same. This comes from differences in tone, highs, lows, pauses, in-breaths, and all of those usual speech-related details. Even more so, obviously, if the reader is different.
This got me thinking: is there a way I could use a recording/an audio file to generate an image? The diagram is simple.
Record > Output audio file > Import audio file to an application > the application reads the audio, analyzes frequencies, and uses that to generate an image based on a preset algorithm (if it allows for variable changes when it comes to the image's creation, that would be best) > output. Of course, one could also just analyze the audio and export it in some automated way into text, which is then used as the input for a program that creates the image from it.
I know there are some random fractal generators that create images based on a pretty basic algorithm. I'm thinking something like that, but not fractal-based. I don't know what - if anything - is out there in this regard.
I looked a bit into some AI-based GAANs and all of that, ML-based animations, such as GANBreeder, but I haven't found anything that can generate an imagetic output from an audio input.
I liked the concept from this music visualization work, and this random walkers tutorial which seems like it could create something I like. I also really enjoyed the creations from this generative art tutorial.
I feel like this post is somehow all over the place, but I hope you get the gist of it. Sometimes it's hard to focus with all these ideas swirling around, so, thanks for reading.
TL;DR: I want to create images, perhaps like the one on top, from audio files. How?
PS: I have zero coding skills, so I'd be looking at mix and matching different apps, if needed, to achieve the desired effect.
Last edited:
