Skip to content

Overview

keepcadence is an AI dubbing platform. It takes a source video or audio file, transcribes it, translates the transcript, synthesises speech in the target language using voice-cloned models, and re-times every sentence so the dub stays in cadence with the original speaker.

  1. Length-hinted translation — the translation prompt includes the source sentence duration so the LLM targets a proportional word count.
  2. Per-sentence TTS duration target — each sentence carries an explicit duration hint fed to the TTS engine.
  3. Pitch-preserving time-stretch — output audio is stretched or compressed up to ±1.20× using a phase-vocoder that preserves perceived pitch.
  4. Forward drift into next silence — residual drift is absorbed by shifting the next silent gap rather than accumulating across sentences.
LayerTechnology
APIHono on Bun (apps/api)
Reconciliation loopHono on Bun (apps/orchestrator)
Job queuePostgres media_job table, FOR UPDATE SKIP LOCKED
ML workersRunPod serverless GPU endpoints (Python)
StorageCloudflare R2
AuthBetter-Auth
  • Runbooks — step-by-step operational procedures: deployment, ASR, TTS, database backups, restore drills, and vendor integrations.
  • Guides (this section) — conceptual overviews aimed at engineers onboarding to the codebase.

Full product documentation (concepts, API reference, user guides) is planned for after MVP launch.