Models

Choose from 24 speech model options.

On this page

Model IDs

# Parakeet and Phonon
parakeet-v3, parakeet-v2, parakeet-redux, phonon-2.5
parakeet-unified, parakeet-eou-320ms

# Other speech models
sensevoice, qwen3-asr, nemotron35, apple-speech
medasr, cohere-transcribe
bodhan-core, bodhan-flex, bodhan-core-int8, bodhan-flex-int8
gemma4-e2b, gemma4-e4b

# Whisper
whisper-tiny, whisper-tiny-english
whisper-small, whisper-small-english
whisper-medium-english, whisper-large-turbo

All 24 identifiers below are supported by --model in 0.8.6.

Example: muesli-cli transcribe interview.m4a --model whisper-small --format json

Transcription Dictionary