Sep 28, 2026 · 1 hr 32 min · 11 segments
Sonic Lab founder Sinan Bokesoy joins The Audio Programmer to ask whether coding still matters when AI agents can write it for you. After 15+ years of building audio plugins, Sinan now has Claude…
Sinan BokesoyGuest
Joshua HodgeHost
I'm not a computer scientist or I didn't study programming or engineering background in computer science.
I studied computer music research and contemporary music so programming applications came out of some creative necessity for me.
I wanted to realize some ideas so and like 25 years ago I maybe yeah almost 30 years ago I studied started studying C sound and then during my PhD studies Max MSP and then later the C++ frameworks became popular I started to learn C++ and realized my first application, which is Cosmos F Saturn, which you can see here.
Yeah, that application, I mean, it's not the version 9 now, but I mean, 15 years ago, it was released version 1.
But I learned a lot from the mistakes of releasing a first product and then creating a support network and then kept staying on the same product for several years and then started to release more and more products.
on what they are doing, different applications, audio processors and instruments, media event generators, and two applications which are AI-assisted, meaning they can they take a prompt and they process it with an LLM and then that prompt generates a script which drives the application itself so And most of them are developed in Jews, but three of them here are developed in unity.
from a necessity of my ideas like I wanted to create 3D visuals so which are very difficult to do in juice you can do of course with OpenGL but the boilerplate programming the OpenGL is very heavy so and these are Unity applications standalone and don't imagine that Unity comes with a DSP framework like Juice does so I had to do everything in-house so create a DSP framework which works in Unity in C sharp and likewise the sound engine is something i have created from scratch for these applications and uh and lately i mean like i consider uh this is the latest application i mean This is a simulation of a spiking neural network which processes live audio directly which comes to the plugin itself.
As an experienced developer and I consider the audio developer different than any other software developer because an audio developer has an artistic vision so we are not just coding so we are designing an instrument we are thinking with the concept and we test the sound so create the presets with a small team around us and we bring the idea in a form of instrument which can be used by other artists.
I'm not a computer scientist or I didn't study programming or engineering background in computer science.
I studied computer music research and contemporary music so programming applications came out of some creative necessity for me.
I wanted to realize some ideas so and like 25 years ago I maybe yeah almost 30 years ago I studied started studying C sound and then during my PhD studies Max MSP and then later the C++ frameworks became popular I started to learn C++ and realized my first application, which is Cosmos F Saturn, which you can see here.
Yeah, that application, I mean, it's not the version 9 now, but I mean, 15 years ago, it was released version 1.
But I learned a lot from the mistakes of releasing a first product and then creating a support network and then kept staying on the same product for several years and then started to release more and more products.
on what they are doing, different applications, audio processors and instruments, media event generators, and two applications which are AI-assisted, meaning they can they take a prompt and they process it with an LLM and then that prompt generates a script which drives the application itself so And most of them are developed in Jews, but three of them here are developed in unity.
from a necessity of my ideas like I wanted to create 3D visuals so which are very difficult to do in juice you can do of course with OpenGL but the boilerplate programming the OpenGL is very heavy so and these are Unity applications standalone and don't imagine that Unity comes with a DSP framework like Juice does so I had to do everything in-house so create a DSP framework which works in Unity in C sharp and likewise the sound engine is something i have created from scratch for these applications and uh and lately i mean like i consider uh this is the latest application i mean This is a simulation of a spiking neural network which processes live audio directly which comes to the plugin itself.
As an experienced developer and I consider the audio developer different than any other software developer because an audio developer has an artistic vision so we are not just coding so we are designing an instrument we are thinking with the concept and we test the sound so create the presets with a small team around us and we bring the idea in a form of instrument which can be used by other artists.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
