Hold bot speech until voicemail detection resolves for outbound calls
# Source: https://github.com/pipecat-ai/pipecat | License: BSD-2-Clause | Copyright 2024–2026, Daily # Provided via justclaw.it.com; keep this notice with the code. # # Copyright (c) 2024-2026, Daily # # SPDX-License-Identifier: BSD 2-Clause License # """Voicemail detection for outbound calls. A bot that places a call needs to know whether a person answered or the call went to voicemail. :class:`VoicemailDetector` listens to what the other side says and asks a classifier; until it has an answer, :class:`TTSGate` holds the bot's speech back so a voicemail greeting is never talked over. Any classifier will do. An :class:`~pipecat.classifiers.llm.classifier.LLMClassifier` needs a service with ``run_inference()``, so a realtime LLM cannot back the detector. """ import asyncio from typing i ... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key