feat(tts): add pocket-tts engine alongside kokoro-fastapi
Some checks failed
Release / Test backend (push) Successful in 36s
Release / Check ui (push) Successful in 50s
Release / Docker / caddy (push) Failing after 45s
CI / Test backend (pull_request) Successful in 39s
CI / Check ui (pull_request) Failing after 11s
CI / Docker / ui (pull_request) Has been skipped
CI / Docker / caddy (pull_request) Failing after 11s
Release / Docker / backend (push) Failing after 48s
Release / Docker / runner (push) Failing after 58s
Release / Upload source maps (push) Failing after 39s
CI / Docker / backend (pull_request) Failing after 34s
CI / Docker / runner (pull_request) Failing after 30s
Release / Docker / ui (push) Successful in 2m42s
Release / Gitea Release (push) Has been skipped

- New backend/internal/pockettts package: POST /tts client for
  kyutai-labs/pocket-tts; streams WAV response and transcodes to MP3
  via ffmpeg so the rest of the pipeline stays format-agnostic
- config.PocketTTS struct + POCKET_TTS_URL env var
- runner.Dependencies.PocketTTS field; runAudioTask routes by voice name:
  pockettts.IsPocketTTSVoice (alba, marius, javert, …) → pocket-tts,
  everything else → kokoro-fastapi
- Dockerfile: runner stage switched from distroless/static to alpine:3.21
  with ffmpeg + ca-certificates installed
- homelab compose: runner gets POCKET_TTS_URL=http://pocket-tts:8000
- Doppler prd + prd_homelab: KOKORO_URL=https://tts.libnovel.cc,
  POCKET_TTS_URL=https://pocket-tts.libnovel.cc
This commit is contained in:
Admin
2026-03-27 16:17:13 +05:00
parent 4831c74acc
commit fea09e3e23
6 changed files with 223 additions and 13 deletions

View File

@@ -26,6 +26,7 @@ import (
"github.com/libnovel/backend/internal/meili"
"github.com/libnovel/backend/internal/novelfire"
"github.com/libnovel/backend/internal/otelsetup"
"github.com/libnovel/backend/internal/pockettts"
"github.com/libnovel/backend/internal/runner"
"github.com/libnovel/backend/internal/storage"
)
@@ -112,10 +113,19 @@ func run() error {
kokoroClient = kokoro.New(cfg.Kokoro.URL)
log.Info("kokoro TTS enabled", "url", cfg.Kokoro.URL)
} else {
log.Warn("KOKORO_URL not set — audio tasks will fail")
log.Warn("KOKORO_URL not set — kokoro voice tasks will fail")
kokoroClient = &noopKokoro{}
}
// ── pocket-tts ──────────────────────────────────────────────────────────
var pocketTTSClient pockettts.Client
if cfg.PocketTTS.URL != "" {
pocketTTSClient = pockettts.New(cfg.PocketTTS.URL)
log.Info("pocket-tts enabled", "url", cfg.PocketTTS.URL)
} else {
log.Warn("POCKET_TTS_URL not set — pocket-tts voice tasks will fail")
}
// ── Meilisearch ─────────────────────────────────────────────────────────
var searchIndex meili.Client
if cfg.Meilisearch.URL != "" {
@@ -151,6 +161,7 @@ func run() error {
SearchIndex: searchIndex,
Novel: novel,
Kokoro: kokoroClient,
PocketTTS: pocketTTSClient,
Log: log,
}
r := runner.New(rCfg, deps)