saidby

Offline-first diarized transcription: a command-line tool and Python library that turns any recording into a transcript with speakers, timestamps, glossary-aware spelling and one audio track per speaker.

Status: pre-alpha. Version 0.1.0 runs the core pipeline: transcription with faster-whisper, diarization with Nemotron-3, word-to-speaker alignment and one aligned audio track per speaker. People identification, glossary correction and review arrive in later 0.x releases.

Install

uv tool install saidby

For machines without an NVIDIA GPU, avoid downloading the CUDA build of PyTorch:

uv tool install saidby --index https://download.pytorch.org/whl/cpu --index-strategy unsafe-best-match

Requirements: ffmpeg on the PATH and, for GPU use, an NVIDIA driver 580 or newer.

Quick start

saidby models pull --all          # one-time download, the only step that uses the network
saidby process call.m4a --out out/ --language es

Each recording gets its own folder under out/:

A failed run keeps .work/ so the next run resumes from the last finished stage; --keep-intermediates keeps it on success too. See docs/cli.md.

Models

Models are never bundled and are only downloaded by an explicit command:

saidby models list
saidby models pull --all

Processing always runs offline (HF_HUB_OFFLINE=1). A Hugging Face token (HF_TOKEN) is needed only for gated models such as pyannote/speaker-diarization-community-1; if the conditions have not been accepted, the error shows the URL where to accept them.

Privacy

• No telemetry leaves the machine. Logs and telemetry are written locally and never contain transcript text, names, glossary terms or voiceprints.
• A test suite blocks any non-loopback network access during processing.

License

Apache-2.0. See LICENSE, NOTICE and MODEL_LICENSES.md. Contributions are accepted under the Developer Certificate of Origin.