106 lines
5 KiB
Markdown
106 lines
5 KiB
Markdown
# Requirements: Nexus v1.6 — Voice Pipeline + Minimal Message Bridge
|
|
|
|
**Defined:** 2026-04-04
|
|
**Core Value:** A fresh onboard asks for ONE thing (root directory), auto-creates PM + Engineer agents, and drops you in the dashboard.
|
|
|
|
## v1.6 Requirements
|
|
|
|
### Voice Pipeline
|
|
|
|
- [x] **VPIPE-01**: User's voice input is transcribed via local Whisper STT with automatic language detection
|
|
- [x] **VPIPE-02**: Agent text responses are synthesized to speech via local Piper TTS in under 3 seconds
|
|
- [x] **VPIPE-03**: Voice pipeline accepts audio from any transport (web chat, Telegram) via a shared VoicePipelineService
|
|
- [x] **VPIPE-04**: Audio from any source is transcoded to WAV 16kHz mono via ffmpeg before Whisper processing
|
|
- [x] **VPIPE-05**: Voice mode flag on messages triggers voice-optimized response formatting (no markdown, natural prose)
|
|
- [x] **VPIPE-06**: Every voice interaction produces dual output: spoken prose response + full text with code blocks
|
|
- [ ] **VPIPE-07**: TTS plays first sentence while subsequent sentences are still synthesizing (sentence-buffered streaming)
|
|
- [ ] **VPIPE-08**: User can synthesize a single text response into multiple language audio outputs (multi-language TTS)
|
|
|
|
### Web Chat Voice
|
|
|
|
- [x] **WCHAT-01**: Mic button in chat input starts/stops voice recording with visual state (idle/recording/processing)
|
|
- [x] **WCHAT-02**: Recording auto-stops on silence detection via VAD (voice activity detection)
|
|
- [x] **WCHAT-03**: Real-time waveform/amplitude visualization displays while recording
|
|
- [x] **WCHAT-04**: Voice response audio plays inline in chat message with audio player controls
|
|
- [x] **WCHAT-05**: User can toggle voice mode: text only / voice input only / full voice (input + output)
|
|
- [x] **WCHAT-06**: Auto-play of voice responses is configurable (on/off in settings)
|
|
|
|
### Telegram Bridge
|
|
|
|
- [ ] **TGRAM-01**: Single Telegram bot relays text messages bidirectionally between user and agents
|
|
- [ ] **TGRAM-02**: Agent replies in Telegram are prefixed with agent identity (e.g. `[PM]`, `[Engineer]`)
|
|
- [ ] **TGRAM-03**: Telegram voice messages are transcribed (OGG → Whisper) and forwarded to agent as text
|
|
- [ ] **TGRAM-04**: Agent responses can be sent back as Telegram voice notes (TTS → OGG)
|
|
- [ ] **TGRAM-05**: Telegram bridge uses long polling (no public HTTPS required)
|
|
- [ ] **TGRAM-06**: Telegram bridge is under 500 lines of code
|
|
|
|
### Onboarding
|
|
|
|
- [ ] **ONBRD-01**: Onboarding hardware probe detects Whisper STT and Piper TTS capability
|
|
- [ ] **ONBRD-02**: Onboarding presents voice enable/skip step based on hardware detection results
|
|
- [ ] **ONBRD-03**: Guided BotFather setup flow for Telegram bot token during onboarding
|
|
|
|
## Future Requirements
|
|
|
|
### Voice Enhancements
|
|
|
|
- **VFUT-01**: Wake word detection ("Hey Nexus") for hands-free activation
|
|
- **VFUT-02**: Real-time speech-to-speech streaming (full-duplex WebSocket)
|
|
- **VFUT-03**: Streaming TTS word-by-word playback
|
|
|
|
### Telegram Enhancements
|
|
|
|
- **TFUT-01**: Deep Telegram ↔ web chat session sync via Postgres event bus
|
|
- **TFUT-02**: Rich Telegram elements (inline keyboards, threaded replies)
|
|
- **TFUT-03**: Per-agent Telegram bots
|
|
|
|
## Out of Scope
|
|
|
|
| Feature | Reason |
|
|
|---------|--------|
|
|
| Real-time speech-to-speech | Entirely different architecture (LiveKit/Pipecat); future milestone |
|
|
| Per-agent Telegram bots | Maintenance nightmare; single bot + agent prefix is correct |
|
|
| Deep Telegram ↔ web chat sync | Requires Postgres event bus; deferred to v2.2 Command Center |
|
|
| Telegram inline keyboards/threads | Thin bridge only; rich elements deferred to Command Center |
|
|
| Wake word detection | Always-on mic; hardware device concern; future |
|
|
| Streaming TTS word-by-word | Audio clicks/gaps; sentence-buffered gives 95% of the benefit |
|
|
| Inline code execution over Telegram | Security risk; bridge is relay only |
|
|
| GSD formatting in Telegram | Stateful session tracking; plain text + Markdown v1 only |
|
|
| Transcription editing before sending | Breaks hands-free flow; show transcript in chat bubble after |
|
|
|
|
## Traceability
|
|
|
|
| Requirement | Phase | Status |
|
|
|-------------|-------|--------|
|
|
| VPIPE-01 | Phase 36 | Complete |
|
|
| VPIPE-02 | Phase 36 | Complete |
|
|
| VPIPE-03 | Phase 36 | Complete |
|
|
| VPIPE-04 | Phase 36 | Complete |
|
|
| VPIPE-05 | Phase 36 | Complete |
|
|
| VPIPE-06 | Phase 36 | Complete |
|
|
| VPIPE-07 | Phase 39 | Pending |
|
|
| VPIPE-08 | Phase 39 | Pending |
|
|
| WCHAT-01 | Phase 37 | Complete |
|
|
| WCHAT-02 | Phase 37 | Complete |
|
|
| WCHAT-03 | Phase 37 | Complete |
|
|
| WCHAT-04 | Phase 37 | Complete |
|
|
| WCHAT-05 | Phase 37 | Complete |
|
|
| WCHAT-06 | Phase 37 | Complete |
|
|
| TGRAM-01 | Phase 38 | Pending |
|
|
| TGRAM-02 | Phase 38 | Pending |
|
|
| TGRAM-03 | Phase 38 | Pending |
|
|
| TGRAM-04 | Phase 38 | Pending |
|
|
| TGRAM-05 | Phase 38 | Pending |
|
|
| TGRAM-06 | Phase 38 | Pending |
|
|
| ONBRD-01 | Phase 39 | Pending |
|
|
| ONBRD-02 | Phase 39 | Pending |
|
|
| ONBRD-03 | Phase 38 | Pending |
|
|
|
|
**Coverage:**
|
|
- v1.6 requirements: 23 total
|
|
- Mapped to phases: 23
|
|
- Unmapped: 0 ✓
|
|
|
|
---
|
|
*Requirements defined: 2026-04-04*
|
|
*Last updated: 2026-04-03 — traceability populated after roadmap creation*
|