Legal

Licences and attribution

Rooster is built on open source work by others. This page credits that work and carries a copy of every licence it is used under. Rooster itself processes your recordings on your Mac.

1. Parakeet TDT 0.6B v3

   NVIDIA

   Speech transcription.

   Converted to Core ML by FluidInference. Rooster uses the converted models unmodified.

   CC BY 4.0 · Source

2. FluidAudio

   FluidInference

   Runs the Parakeet models on the Apple Neural Engine.

   Apache 2.0 · Source

3. NeMo Text Processing

   Copyright (c) NVIDIA CORPORATION & AFFILIATES

   Normalises numbers and dates in transcripts.

   Compiled into the text-processing-rs framework used by FluidAudio.

   Apache 2.0 · Source

4. whisper.cpp

   Copyright (c) 2023-2026 The ggml authors

   Transcription for languages Parakeet does not cover.

   MIT · Source

5. DeepFilterNet

   Copyright (c) 2021 Hendrik Schröter

   Studio Sound noise removal.

   MIT · Source

Transcription models you supply

Rooster can transcribe with a Whisper model file that you download and choose yourself. Those model files are not distributed with Rooster, so they are covered by whatever licence you obtained them under.

Corrections

If a credit here is wrong or incomplete, please tell us and we will correct it.