Files

T

kaneda 9deeedf5b3 feat(voice): modalità dialogo — voce continua hands-free (v0.2.0)

- Nuovo VoiceRecorder (QAudioInput, PCM 16 bit mono): analisi del livello
  in tempo reale e stop automatico dopo il silenzio (pausa e soglia
  configurabili dalle impostazioni); produce WAV per /api/transcribe;
  emette failed("no-speech") se non rileva voce (cattura scartata)
- ChatPage: modalità dialogo (menu "Voice mode"): ascolto -> trascrizione
  -> invio -> lettura della risposta -> riascolto in ciclo; tocco sul
  testo di stato per uscire; limite di 3 errori consecutivi poi esce
- Dettatura manuale: invio automatico dopo la trascrizione (opzione,
  default attivo, disattivabile)
- Settings: sezione "Voice dialog" (auto-invio, pausa auto-stop,
  sensibilità microfono)
- Il percorso di dettatura manuale (Recorder OGG) resta invariato

2026-09-12 09:14:25 +02:00

1.3 KiB

Raw Blame History

harbour-hermes

Native Sailfish OS client for the Hermes Web UI (hermes-webui): chat with your Hermes agent from the phone — and use it with your voice.

Features

Sign in to your Hermes Web UI (session cookie persisted; password never stored)
Sessions list, new session, open any session
Chat with live streaming replies (SSE token deltas)
Voice dictation: tap Mic, speak, tap Stop → server-side Whisper transcription lands in the composer
Read aloud: server-side TTS (edge engine, Italian voices) played through QMediaPlayer; optional auto-read of every completed reply
Cancel a running turn, resync from server state, cover page

Requirements

Sailfish OS 4.4+ (developed against Sailfish 5.1)
A running hermes-webui instance reachable over HTTPS (default: https://hermes.hackatoniclife.com)
Sailjail permissions Internet;Audio;Microphone (declared in the .desktop)

Build

See docs/BUILD.md (Sailfish SDK, sfdk build / sfdk deploy) and docs/PROTOCOL.md for the HTTP/SSE protocol the app speaks (validated live against a real instance).

Status

Version 0.2.0 — protocol and C++ core validated against a real hermes-webui (login, sessions, streaming chat, TTS, STT); on-device testing (audio paths, Sailjail prompts, keyboard handling) still pending.