MedITron/PTSRaiAgent
4
0
Fork 0
Code Issues 21 Pull Requests Actions Packages Projects Releases Wiki Activity
154 Commits 20 Branches 0 Tags
50b48a7290fa364a809a17ceabebea67b760a836
Commit Graph
3 Commits
Author SHA1 Message Date
ElebobaandClaude Opus 5.5 f19ea33937 feat: SaluteSpeech STT for the pilot + no foreign STT outside the demo (ADR-016)
CI / ruff · pytest (pull_request) Successful in 2m16s
Details 
Refs #121

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-31 17:11:44 +03:00
ElebobaandClaude Opus 5.5 d700608825 fix(llm): STT prompt that keeps unclear speech; reasoning off (~60 s → ~3 s)
CI / ruff · pytest (pull_request) Successful in 2m23s
Details 
Live check on synthetic speech (espeak) via OpenRouter gemini-2.5-flash:
3–5 s per clip, silence → no speech.

Refs #116

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-31 11:29:40 +03:00
ElebobaandClaude Opus 5.5 7443b61974 feat(llm): speech-to-text for patient voice input via OpenRouter (+ offline mock)
CI / ruff · pytest (pull_request) Successful in 2m57s
Details 
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