94e2ca1902
Follow-up test call: no more cancelled replies, but 3-5s response gaps on
turns the smart-turn model judged INCOMPLETE ("I'm due to my annual exam.") -
it waited the library-default 3s of silence before triggering the LLM. Build
the stop strategy explicitly with SmartTurnParams(stop_secs=1.5), env-tunable.
A caller who really does resume just yields a follow-up turn, which is safe
now that interruption broadcasts are off.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
78 lines
4.5 KiB
Plaintext
78 lines
4.5 KiB
Plaintext
# Copy to .env and fill in. run.sh auto-loads it.
|
|
|
|
# ── Public ingress (Twilio dials this back) ──────────────────────────────────
|
|
# Public hostname; nginx terminates TLS here and proxies to the app. Must match the
|
|
# Twilio webhook host (Twilio signs https://PUBLIC_HOST/voice).
|
|
PUBLIC_HOST=voip.activeblue.net
|
|
PORT=8200
|
|
# App bind address. Default 127.0.0.1 (nginx proxies in locally) — not exposed on LAN.
|
|
BIND_HOST=127.0.0.1
|
|
|
|
# ── Twilio ───────────────────────────────────────────────────────────────────
|
|
# From console.twilio.com. Used to auto-hang-up the carrier leg and (recommended)
|
|
# validate inbound webhook signatures. Twilio signs webhooks with the Auth Token, so
|
|
# signature validation must use the Auth Token (not an API Key Secret).
|
|
TWILIO_ACCOUNT_SID=ACxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
|
TWILIO_AUTH_TOKEN=your_auth_token_here
|
|
# Inbound webhook signature validation is ON whenever TWILIO_AUTH_TOKEN is set.
|
|
# Set to false only for local testing without real Twilio requests.
|
|
TWILIO_VALIDATE=true
|
|
# Shared secret embedded in the Media Stream wss URL to gate /ws. Set a stable random
|
|
# value (e.g. `openssl rand -base64 24`); if blank, one is generated per process start.
|
|
STREAM_TOKEN=
|
|
|
|
# ── Odoo appointment integration ─────────────────────────────────────────────
|
|
# Leave ODOO_USER/ODOO_API_KEY blank to disable Odoo and log requests to JSONL only.
|
|
# Same creds the activeblue-agent container uses (docker inspect activeblue-agent).
|
|
# Verified working against db1 with ODOO_TARGET=crm.
|
|
ODOO_URL=http://localhost:8069
|
|
ODOO_DB=db1
|
|
ODOO_USER=mr.garcia09@gmail.com
|
|
ODOO_API_KEY=
|
|
ODOO_TARGET=crm # crm = callback lead (recommended) | calendar = tentative event
|
|
|
|
# ── Capacity ─────────────────────────────────────────────────────────────────
|
|
# Max simultaneous calls (each uses GPU; Ollama serializes generation). Over-cap
|
|
# callers hear BUSY_MESSAGE and are hung up. Tune to your GPU headroom (2-3 typical).
|
|
MAX_CONCURRENT_CALLS=2
|
|
# BUSY_MESSAGE=Thank you for calling Advanced Vision Care. All of our lines are busy right now. Please call back in a few minutes. Goodbye.
|
|
|
|
# ── Models (defaults are fine) ───────────────────────────────────────────────
|
|
OLLAMA_MODEL=llama3.1:8b
|
|
OLLAMA_URL=http://127.0.0.1:11434/v1
|
|
# LLM provider: ollama (local, default) | anthropic (Claude API). Flip to A/B test Claude.
|
|
LLM_PROVIDER=ollama
|
|
ANTHROPIC_API_KEY=
|
|
# Default is the most capable model; for low-latency phone voice prefer claude-haiku-4-5
|
|
# (fastest) or claude-sonnet-4-6 (balance).
|
|
ANTHROPIC_MODEL=claude-opus-4-8
|
|
# ── STT: Whisper (faster-whisper, real-time in-call) ─────────────────────────
|
|
WHISPER_MODEL=base
|
|
WHISPER_DEVICE=cuda
|
|
WHISPER_COMPUTE=float16
|
|
KOKORO_VOICE=af_heart
|
|
KOKORO_MODEL_DIR=/home/tocmo0nlord/pipecat-run/models
|
|
|
|
# ── Call behaviour ───────────────────────────────────────────────────────────
|
|
AGENT_NAME=AVA
|
|
# How the name is SPOKEN (TTS only; logs/Odoo keep AGENT_NAME). "Eva" -> "EE-vuh".
|
|
AGENT_NAME_SPOKEN=Eva
|
|
# Grace pause after the goodbye before the carrier leg is dropped (seconds).
|
|
HANGUP_DELAY_SECS=4.0
|
|
# Half-duplex: ignore caller audio while the agent speaks (+ tail) so its own echo on the
|
|
# phone line can't trigger a false barge-in that cancels its reply. false = allow barge-in.
|
|
HALF_DUPLEX=true
|
|
ECHO_TAIL_SECS=0.25
|
|
# VAD kept sensitive (half-duplex gates echo, so this only affects the caller's turn).
|
|
VAD_CONFIDENCE=0.5
|
|
VAD_MIN_VOLUME=0.15
|
|
VAD_START_SECS=0.1
|
|
VAD_STOP_SECS=0.5
|
|
# Extra silence the smart-turn analyzer waits when it judges an utterance INCOMPLETE
|
|
# before ending the turn anyway (library default 3s caused ~3.5s dead air on some turns).
|
|
#SMART_TURN_STOP_SECS=1.5
|
|
# Deterministic slot memory (callstate.py): injects an ALREADY-COLLECTED / STILL-NEEDED
|
|
# checklist into the system prompt each turn + merges VAD-fragmented user turns, so the
|
|
# local 8B stops re-asking for name/reason/phone. Default: on for ollama, off for anthropic.
|
|
#CALL_STATE_TRACKING=true
|