Model selection for Transcription
Via our Klangio API for transcription we offer you a range of models to select from, to optimize the transcription process. Here you find further details and guidance on which model to choose for your use-case.
Overview
| Model Identifier | Description |
|---|---|
detect | Utilizes the instrument detection capabilities of the Klangio AI to select the best suitable model. |
universal | A general-purpose transcription model that will extract hearable notes from the song. Specialized models yield better results. |
piano | Optimized for audio consisting mainly of piano. |
guitar | Optimized for audio consisting mainly of guitar. |
bass | Optimized for audio consisting mainly of bass guitar. |
vocal | Optimized for audio consisting mainly of vocal. |
lead | Will extract the overall melody and chords played in the audio. |
drums - new | Optimized for audio consisting mainly of drums |
wind - new | Optimized for audio consisting mainly of wind instruments like sax, flute, recorder, trumpet, etc. |
string - new | Optimized for audio consisting mainly of string instruments like violin, viola or cello |
piano_arrangement - new | Creates a piano arrangement based on the provided audio |