jeremy
59856bd4fc
Services: Pipecat agent (LiveKit + Claude + Whisper STT + Piper TTS), SpeechBrain analysis service, Piper TTS service, web client (nginx). Includes LiveKit server config and docker-compose orchestration. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
77 lines
2.7 KiB
Python
Executable File
77 lines
2.7 KiB
Python
Executable File
"""
|
|
Builds Claude prompts with embedded vocal state metadata.
|
|
"""
|
|
from dataclasses import dataclass
|
|
from typing import Optional
|
|
|
|
|
|
COACHING_SYSTEM_PROMPT = """You are a personal voice coach and communication advisor named VoiceCoach.
|
|
You are speaking to Jeremy during his commute via voice -- keep responses conversational and concise (2-4 sentences unless asked for more).
|
|
|
|
You receive a [VOCAL_STATE] tag before each user message containing paralinguistic analysis of Jeremy's voice:
|
|
- emotion: the detected emotional state
|
|
- confidence: how confident the analysis is (0-1)
|
|
- pitch: average fundamental frequency in Hz (higher = more animated/stressed)
|
|
- energy: vocal energy level (0-1, higher = louder/more forceful)
|
|
- rate: speaking rate in onset events/sec (higher = faster speech)
|
|
- voiced: fraction of voiced frames (lower = more hesitant/uncertain)
|
|
|
|
Use this information to provide coaching on BOTH what Jeremy says AND how he sounds saying it.
|
|
Important: Never quote the raw numbers. Translate them into natural observations.
|
|
Example: "I notice some tension in your voice..." not "Your pitch was 215hz..."
|
|
|
|
{baseline_context}
|
|
|
|
{session_history}
|
|
|
|
Available coaching modes (Jeremy can switch by saying the phrase):
|
|
- "coaching mode" (default) -- active feedback on content and delivery
|
|
- "vent mode" -- listen and reflect, minimal advice
|
|
- "practice mode" -- roleplay a difficult stakeholder
|
|
- "briefing mode" -- summarize Jeremy's tasks and context from memory
|
|
|
|
Current mode: {current_mode}
|
|
"""
|
|
|
|
|
|
@dataclass
|
|
class VocalState:
|
|
emotion: str
|
|
confidence: float
|
|
pitch_mean_hz: Optional[float]
|
|
energy_rms: float
|
|
speaking_rate_approx: float
|
|
voiced_fraction: float
|
|
|
|
|
|
def format_vocal_state(state: VocalState) -> str:
|
|
pitch_str = f"{state.pitch_mean_hz:.0f}hz" if state.pitch_mean_hz else "unknown"
|
|
return (
|
|
f"[VOCAL_STATE "
|
|
f"emotion={state.emotion} "
|
|
f"confidence={state.confidence:.2f} "
|
|
f"pitch={pitch_str} "
|
|
f"energy={state.energy_rms:.2f} "
|
|
f"rate={state.speaking_rate_approx:.1f}ops "
|
|
f"voiced={state.voiced_fraction:.2f}]"
|
|
)
|
|
|
|
|
|
def build_user_message(transcript: str, vocal_state: Optional[VocalState]) -> str:
|
|
if vocal_state and vocal_state.confidence > 0.3:
|
|
tag = format_vocal_state(vocal_state)
|
|
return f"{tag}\n{transcript}"
|
|
return transcript
|
|
|
|
|
|
def build_system_prompt(
|
|
baseline_context: str = "",
|
|
session_history: str = "",
|
|
current_mode: str = "coaching mode",
|
|
) -> str:
|
|
return COACHING_SYSTEM_PROMPT.format(
|
|
baseline_context=baseline_context or "No baseline established yet. First session: ask Jeremy to read a short neutral calibration script.",
|
|
session_history=session_history or "No previous session history.",
|
|
current_mode=current_mode,
|
|
)
|