DSP Archives - Christian's private site

Pocket-sized speech, in Go

Kyutai’s PocketTTS is a text-to-speech model small enough to run on a CPU. Its reference implementation is Python and PyTorch. go-pocket-tts runs the same model as a single Go binary: it reads the safetensors weights directly and needs neither Python nor ONNX Runtime.

It got one sentence in Audio on Linux, in Go. It deserves more than that, because upstream has moved on since then: a September model, German, a 24-layer variant and a new kind of sampler. This weekend I brought the port up to upstream v3.3.0. That came to 25 pull requests and 116 commits in two days, and German is part of it.

go-sofa and go-hdf5: how a head hears, in pure Go

A SOFA file describes how a head hears. SOFA (Spatially Oriented Format for Acoustics, standardised as AES69) stores head-related transfer functions: for hundreds or thousands of directions, the impulse response from a loudspeaker at that direction to a microphone in each ear. With such a set you can place any sound anywhere around a listener on headphones. I wrote my first SOFA reader, PasSofa, in Object Pascal in 2017, and ported it to JavaScript as WebSofa. Now there is go-sofa, which reads and writes SOFA files in pure Go, on top of my fork of a pure-Go HDF5 library, go-hdf5. Both started in February. On the last weekend of September they got about 230 commits and 39,000 added lines. Every figure in this post was made by a Go program that reads the files with go-sofa or go-hdf5.

Fast Fourier transforms at awkward lengths

Every FFT library is fast at 1024. The interesting question is what happens at 1009.

algo-fft — the FFT library in my algo-* suite — is at v0.7.3. This post is a full measurement of where it stands: against FFTW3, against the other Go FFT libraries, at powers of two and at the lengths that are actually awkward, with and without its assembly.

Audio on Linux, in Go

The VST years were a Windows story. My current audio experiments live somewhere else entirely: on Linux, inside the PipeWire graph, written in Go — and the parallels to the old days are almost comically direct.

gll-tools: measurement, modernized

The measurement thread from the retrospective never ended — it moved to Go. gll-tools is a Go library and a set of CLI tools for reading EASE GLL (Generic Loudspeaker Library) data, the format the pro-audio world uses to describe loudspeaker directivity and behavior.

algo-*: a DSP suite in Go

Fast forward to today. Most of my current code is written in Go, and the largest chunk of it is a family of DSP libraries under the algo-* umbrella — the direct descendant of everything the retrospective posts described, rebuilt on a modern stack.

Measure everything

If plugins were the fun side of DSP, measurement was the honest side. You can convince yourself a filter sounds good; you cannot argue with its magnitude response. Over the years I built a small arsenal of measurement tools and published a collection of measurements made with them.

SynthEdit modules and tools

Here is a confession right away: I have never actually used SynthEdit to make music. But I was fascinated by how it worked — a modular environment where third-party modules (SEMs) plug into a visual synthesis graph. So I did what I always do with fascinating architectures: I took it apart and built for it. The results live under SE modules and SE Tools.

The VST plugin years

Everything on this site ultimately traces back to one obsession: audio. So it feels right to start this little retrospective series where my public work started — with VST plugins, written in Object Pascal, one filter and one waveshaper at a time.