PatientDesk / patientdesk/duyu-1
Duyu - access through LLMTR
Duyu is PatientDesk's speech-to-text model for Turkish. It transcribes wav, mp3, m4a, webm, ogg and flac recordings and can return plain text, JSON with segment and word timestamps, SRT or VTT. A spelling hint can be sent for terms such as drug or person names. Audio is sent base64-encoded in the request body, up to about 9 MB per request. It is free, with a daily usage limit, until October 25, 2026, when it is retired.
Technical specifications
| Canonical ID | patientdesk/duyu-1 |
|---|---|
| Provider | PatientDesk |
| Context window | Not available |
| Operations | AUDIO_TRANSCRIPTIONS |
| Modalities | audio, text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| AUDIO_TRANSCRIPTIONS | INPUT_AUDIO | PER_MINUTE | Not available |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"patientdesk/duyu-1","messages":[{"role":"user","content":"Hello"}]}'Related models
- Alania patientdesk/alania-v1
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Trendyol Asure 12B llmtr/trendyol-asure-12b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Muse Glimmer 30B (Turkey) llmtr/muse-glimmer-30b-tr
- EmbeddingGemma 300M llmtr/embeddinggemma-300m
- Qwen 3.5 4B llmtr/qwen3-5-4b