PatientDesk | Duyu | Speech to Text.
- PatientDesk
- Voice to Text
- $0.000034722222 per second
PatientDesk Duyu turns Turkish speech into text from audio files, with optional spelling hints for names and specialist terms in transcription workflows.
What PatientDesk | Duyu | Speech to Text is good at.
Related modelView modelAlibaba | Qwen3 ASR Flash Filetrans | Speech to Text
Run it on the same input to compare output, speed and price.
Model documentation
About this model
PatientDesk Duyu turns Turkish speech into text from audio files, with optional spelling hints for names and specialist terms in transcription workflows.
Questions about this model
The short answers. For anything specific to your setup, talk to our team.
PatientDesk Duyu Speech to Text converts Turkish speech recordings into written transcripts. It accepts an audio file URL and returns structured transcription output, including the audio duration. The model supports WAV, MP3, M4A, WebM, OGG and FLAC files, with limits of 100 MB and two hours per recording.
PatientDesk Duyu Speech to Text is intended for workflows that need written text from Turkish speech recordings. Teams can provide an audio URL and optionally add a spelling hint for names or specialist vocabulary. On each::labs, the model returns structured output that can feed subsequent text-processing steps.
PatientDesk Duyu returns a transcript and audio duration in structured output. Pricing is based on the duration of the submitted audio rather than the time taken to process it, at $0.125 per audio hour. Language can be set to Turkish or automatic detection, and an optional prompt supplies spelling or vocabulary hints.