## Port of a port

[Pocket TTS Deno](https://codeberg.org/bytetrie/pocket-tts-deno) takes the very
easy to use browser implementation
[pocket-tts-onnx](https://github.com/KevinAHM/pocket-tts-onnx-export) of the
efficient [Kyutai Pocket TTS](https://huggingface.co/kyutai/pocket-tts) project.
I borrowed the idea for the OpenAI-like API from another port,
[pocket-tts-server](https://github.com/ai-joe-git/pocket-tts-server). In this
case, I pointed Claude to those projects and guided it towards a functional
port.

## Accents

I wanted to explore the use of voice cloning in some of my projects. Many of the
voices I've tried this with sound more realistic compared to the state of the
art from before 2022. However, the model definitely has difficulty with
replicating the Australian accent. Using my own voice, it seems to make it sound
very American. "Very Australian" accents[^5] can't seem to get replicated nicely
at all, they sound robotic and the American bias comes through and breaks the
coherence.[^1] My best experiments come from using Eastern European type voices.

This model seems to be very "community-centric" with many ports, and also new
models that support languages other than the core languages by the Kyutai team.[^2]
I've also experimented with another port optimized for my phone, which on that
hardware works much better.[^3]

## Jargon

Other than the accent issue it struggles with certain kinds of words,
specifically jargon. However, for things like symbols and abbreviations it just
detects those and converts them into full words. It would be useful to use a
local model to convert the user's input (or a program's output) into exactly
what the model can handle.[^4]

I will continue to explore using this as part of a personal assistant tool.

[^1]: Perhaps the solution is to train a model specifically on voices that sound
    more Australian (or even, British and Irish).

[^2]: I'm not sure they're planning to support all languages.

[^3]: Although the onnx / wasm models work on my phone, they're really slow, and
    seem to use a lot of power. This other port is instant, and also allows me
    to use a pre-generated voice embedding, which loads faster than having to
    rely on a wav file for the voice.

[^4]: I experimented a bit with my own mappings and also trying to formulate the
    right context, and it worked OK, even with some phonetic approaches.
    However, I'm sure there's even better approaches regarding how tokenization
    works so I'll need to research all of this further.

[^5]: My accent isn't a classic, strong Austrlian accent due to growing up in
    Sydney, and living in Europe for many years.