ElebobaandClaude Opus 5.5 7443b61974 feat(llm): speech-to-text for patient voice input via OpenRouter (+ offline mock) ...

POST /api/v1/me/{token}/stt takes a 16 kHz mono WAV and only transcribes:
the patient checks the text and sends it as an ordinary message, so safety,
scrub() and the LLM gateway still apply. Audio is neither stored nor logged.
OpenRouter STT is synthetic-data only (ADR-014); SaluteSpeech for the pilot is #121.

Refs #116

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-31 11:19:55 +03:00

..

clinical

fix(clinical): red flags, one crisis rule, callback after a crisis, one table of numbers

2026-10-04 16:21:16 +03:00

dev

chore(core): stage 1 contracts — dialog, API schemas + fixtures, integrations, monitoring, modules

2026-10-03 15:22:25 +03:00

info

docs(rag): describe RAG approach for Minzdrav clinical guidelines

2026-10-04 07:57:00 +03:00

mock

docs(product): mockups brief and the design mockups of the patient app

2026-10-04 09:12:05 +03:00

product

docs(product): mockups brief and the design mockups of the patient app

2026-10-04 09:12:05 +03:00

source

fix(llm): RAG citation pages, scrub placeholders, disease-aware document choice

2026-10-04 04:31:59 +03:00

DECISIONS.md

feat(llm): speech-to-text for patient voice input via OpenRouter (+ offline mock)

2026-10-31 11:19:55 +03:00