00/Docs

How the pipeline actually works.

This is an early set of docs — CLI usage, pipeline stages, execution providers, and the model manifest. A full reference lands with v1.

01/CLI quickstart

The CLI runs the same pipeline the desktop app runs.

No separate headless engine, no feature gap — same stages, same models, scriptable for batch localization or CI. Included on every tier, Free included.

trackdub dub --media ./video.mp4 --target-language es
trackdub dub --media ./video.mp4 --target-language de \
  --model asr:whisper-small --model tts:kokoro-onnx
trackdub dub --preset my-preset --input-dir ./videos

Re-running the same project skips already-completed stages — only what changed reruns.

02/Pipeline stages

Six stages. Each one a real, inspectable artifact.

  1. 01
    Ingest
    Probe the container, extract audio, detect scenes and speech.
  2. 02
    Transcribe
    Source-language ASR with word-level timestamps.
  3. 03
    Translate
    Per-line MT against an editable target script and glossary.
  4. 04
    Diarize
    Cluster speakers, attach a voice reference to each.
  5. 05
    Voice
    Per-speaker zero-shot TTS. Any single line can regenerate on its own.
  6. 06
    Mix
    Align to source timing, duck under preserved music/SFX, mux the export.

Full interactive walkthrough on the homepage.

03/Execution providers

Fallback is per-stage, not per-project.

A missing provider on one stage doesn't disable the rest of the pipeline — each stage picks the fastest provider your hardware supports and falls back on its own.

TensorRT RTX
Windows · RTX 30/40/50

Auto-selected on supported GPUs.

DirectML
Windows · any DX12 GPU

Broadest Windows GPU coverage, incl. Intel Arc, AMD Radeon.

CUDA
Windows / Linux · NVIDIA

Used on non-RTX NVIDIA cards.

CoreML
macOS · Apple Silicon

Neural Engine + GPU, auto-selected on M-series.

CPU (ONNX Runtime)
All platforms

Always available. No GPU required to complete a project.

04/Model manifest

Every bundled model, declared — not implied.

bundled-models.manifest.json lists every model Trackdub ships: task, license, whether commercial use is allowed, and a checksum. No research-only or non-commercial-only checkpoint ships in any tier.

VAD
ASR
Diarization
Translation
TTS
Source separation
Forced alignment
Lip sync
05/More

Full API and SDK reference lands with v1.

Building something against the pipeline now? Write to hello@trackdub.com and we'll loop you in as it ships.