SnicksnackLicenses
Snicksnack stands on the shoulders of others. Thanks to everyone who shares their work.
Klang Pianissimo
The Swedish speech model: KlangAI/pianissimo-sv by Klang, a fine-tune of NVIDIA Parakeet TDT 0.6B v3. Both under CC BY 4.0. Snicksnack uses a converted version (Core ML with int8 weights). Klang and NVIDIA do not endorse the app.
NVIDIA Parakeet TDT 0.6B v3
English and 23 other European languages: nvidia/parakeet-tdt-0.6b-v3, under CC BY 4.0, converted to Core ML by FluidInference. NVIDIA and FluidInference do not endorse the app.
Speaker diarization
pyannote community-1 (speaker-diarization-community-1) by pyannote, with speaker embeddings from WeSpeaker and PLDA parameters from BUT Speech@FIT, under CC BY 4.0, converted to Core ML by FluidInference. pyannote, WeSpeaker, BUT and FluidInference do not endorse the app.
FluidAudio
FluidAudio by FluidInference, under the Apache License 2.0.
Fonts on this website
Newsreader by Production Type and Nunito by Vernon Adams and others, both under the SIL Open Font License 1.1.