Long-form story-writer with canon-keeping, sequel-continuity, and self-hosted narration. Database-is-source-of-truth — writer is the tooling.
Kayos
465c94b745
TTS layer landed as schema-only — synthesis pipeline ships in v0.2. Putting the tables in v0.1 means imports already carry the right shape; we won't need a 'migrate every existing story' pass later. Decisions locked 2026-05-13: - Engine: F5-TTS (best 8GB FOSS option, mid-2026 SOTA) - Default voice source: LJ Speech (Linda Johnson, PD released specifically for TTS training — airtight for sharing/uploading generated audio. The 'AI-consent-released' license posture is the difference between 'should be fine' and 'definitely fine.') - Variety voices: Hi-Fi TTS speaker IDs (Apache 2.0, same consent shape). LibriVox is optional but never default. - Pronunciation overrides DB layer (story-scoped + global) to fix proper-noun mispronunciation — the actual TTS-quality gap on Cobb's bar of 'must not wake me up.' Pre-pass with Opus extracts proper nouns + IPA, operator verifies, table caches forever. Tables: - voices — name, license, reference_path/text, sample_rate, default flag - pronunciation_overrides — story-scoped or global, IPA/arpabet - narration_runs — TTS audit trail mirroring generation_runs - stories.preferred_voice_id FK Unique constraints: - one default voice (partial index) - one row per (story, word) override - one global row per word |
||
|---|---|---|
| migrations | ||
| skald | ||
| skald-core | ||
| .gitignore | ||
| Cargo.lock | ||
| Cargo.toml | ||
| compose.yml | ||
| Dockerfile | ||
| entrypoint.sh | ||
| README.md | ||
skald
Long-form story-writer with canon-keeping, sequel continuity, and (future) self-hosted audiobook narration. Database is the source of truth — the writer is the tooling.
Named for the Old Norse poets who composed and memorized kings' sagas across generations.
Status: v0.1 — scaffold
What's wired:
- Rust workspace (
skald-core+skald) - Postgres schema for stories, characters, canon facts, chapters, passages, generation runs, audit findings, tags
- pgvector extension installed for future similarity search
skald import-markdowningests a story file (chapters + bible) into the schemaskald serveexposes/healthand runs migrations on boot- Single-container deploy: postgres + skald in one image
Not yet wired:
- Web UI (the inbox + browse + queue surface)
- clawdforge calls (the actual generate / cleanup / canon-audit pipeline)
- Embeddings + similarity search
- TTS sidecar
v0.1 smoke
docker compose -p skald up -d
docker exec skald skald import-markdown \
--path /seed/coast-down.md \
--title "The Coast-Down"
curl http://lucy:7780/health
# → { ok: true, db_ok: true, story_count: 1, ... }
Schema (cheat sheet)
stories → meta + status + parent/root for series
characters → real or fictional, story-scoped
canon_facts → setting, mystery, theme, rule, historical_anchor, hook
chapters → full prose body
chapter_summaries → short summaries for cheap context loading
passages → paragraph-level + embedding vector(1536)
generation_runs → every LLM call logged
audit_findings → canon audit output (severity + area)
tags → arbitrary labels
Architecture (v0.1 + the plan)
┌─────────────────────────────────┐
│ skald container │
│ ┌───────────┐ ┌────────────┐ │
│ │ postgres │ │ skald-rust │ │
│ │ pgvector │←─│ axum + cli │ │
│ │ localhost │ │ :7780 │ │
│ └───────────┘ └─────┬──────┘ │
└─────────────────────────┼────────┘
│ HTTP (future)
↓
┌──────────┐
│clawdforge│
└─────┬────┘
↓
opus calls
v1.0+: extract postgres to its own container on db-net. skald
becomes pure stateless rust, connects via DATABASE_URL. Migration
is a connection-string change + a network move; the binary doesn't
care where the DB lives.
License
MIT.