| title: Patient Virtuel · Hygiéniste Pro | |
| emoji: 🦷 | |
| colorFrom: orange | |
| colorTo: dark | |
| sdk: gradio | |
| sdk_version: 5.0 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| # Patient Virtuel · Hygiéniste Pro | |
| A voice-based French practice tool for dental hygienists. Roleplay a 60-minute hygiene session with a Swiss virtual patient, then receive structured grammar and vocabulary feedback. | |
| **Backyard AI** — built for a real learner training at a Swiss clinic. | |
| ## How it works | |
| 1. Press the mic button and speak in French to the patient | |
| 2. The patient responds naturally, using Swiss-French regionalisms | |
| 3. When you say "Fin de la séance", the app switches to tutor mode | |
| 4. Receive a structured recap with corrections and explanations | |
| ## Model credits | |
| - **LLM**: [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) via Modal (A100 GPU) — Apache 2.0 | |
| - **TTS**: [mistralai/Voxtral-4B-TTS-2603](https://huggingface.co/mistralai/Voxtral-4B-TTS-2603) via Mistral API — CC-BY-NC 4.0 (non-commercial demo) | |
| - **STT**: [faster-whisper-large-v3-turbo](https://github.com/SYSTRAN/faster-whisper) via Modal (A10G GPU) — MIT | |
| ## License disclaimer | |
| The TTS model (Voxtral-4B-TTS-2603) is licensed under CC-BY-NC 4.0. This Space is a non-commercial demonstration. All other components are Apache 2.0 or MIT licensed. | |
| ## Environment variables | |
| | Variable | Purpose | | |
| |---|---| | |
| | `MODAL_ENDPOINT_QWEN` | Modal endpoint for Qwen LLM | | |
| | `MODAL_ENDPOINT_WHISPER` | Modal endpoint for Whisper STT | | |
| | `MODAL_AUTH_TOKEN` | Shared auth token (matching Modal's EXPECTED_TOKEN) | | |
| | `MISTRAL_API_KEY` | Mistral API key for Voxtral TTS | | |