Pain Tracker can fill diary entries from short text messages and Telegram voice notes. Text is processed by a lightweight recognition model. Voice notes are transcribed first, then passed through the same extraction flow.
How It Works
- Text messages go directly to the recognition model.
- Telegram voice messages are transcribed first, then parsed into fields such as pain level, triggers, medications, symptoms, and pain location.
- The recognized data is used to fill the log automatically.
Examples
- Text: "Yesterday 6/10 on the left, stress, took ibuprofen, helped."
- Voice note: "Pain level 6 on the right after office took sumatriptan."
Supported Languages
- Best supported end-to-end languages: English, German, and Russian.
- Set your app language to the same language you write or speak.
- Other languages may partially transcribe, but they are not currently supported in the full recognition flow.
Current Limitations
- Voice recognition currently works with Telegram voice messages.
- Voice messages longer than 30 seconds or larger than 5 MB are rejected.
- Background noise, multiple speakers, very fast speech, mixed languages, or long unstructured stories can reduce accuracy.
- AI can miss details or put them into the wrong field.
Best Results
Keep messages short and structured.