skald/README.md

39 lines
1.4 KiB
Markdown

# skald — `engine/kokoro` variant
This branch is the **Kokoro-82M TTS backend** variant of
[skald](https://git.sulkta.com/Sulkta-OSS/skald). It carries
engine-specific tuning for Kokoro that doesn't generalise to the
other backends; everything else tracks `main`.
For the full project — the story-writer, the schema, the narration
pipeline — see `main` and the root `README.md`.
## What's different here
Kokoro-82M is the fast, audiobook-quality narrator. At 82M
parameters it's tiny and quick (~50x real-time on a modest GPU) but
has a couple of rough edges this branch works around in
`engines/kokoro/server.py`:
- **Question prosody** — single `?` reads flat, so interrogatives
get a stronger rising contour applied at synth time.
- **Pacing gaps** — paragraph / scene / breath gap durations tuned
for long-form prose narration.
- **Pronunciation respellings** — Kokoro's phonemizer treats
consecutive capitals as initialisms, so proper-noun respellings
are seeded lowercase-syllabified.
## Usage
The Kokoro sidecar speaks the same `POST /synthesize` + `GET
/healthz` contract as the other engines (see `engines/README.md`).
Point skald's `KOKORO_URL` at it and route `kokoro_*` voices to it.
```bash
docker compose up -d # skald + postgres
# bring up the Kokoro sidecar from engines/kokoro/
```
## License
AGPL-3.0-or-later — see `LICENSE`.