Pipecat

by Daily.co

Open-source framework for voice and multimodal conversational AI agents.

TL;DR

Open-source framework for voice and multimodal conversational AI agents.

Best for developers building self-hosted voice agents with explicit control over the stack. Pricing: free.

What it is

Pipecat is an open-source Python framework from Daily.co for building realtime voice and multimodal AI agents. It composes pipeline stages — VAD, ASR, LLM, TTS, function calls — over WebRTC or WebSocket transport. Pipecat is the open alternative to Vapi or Retell for teams that want full ownership of the runtime, model choice, and cost model. BSD-2-Clause licensed.

Best for: Developers building self-hosted voice agents with explicit control over the stack.
Watch out for: DIY; you operate the media transport, model selection, and scaling.

Install / use

pip install pipecat-ai

Features

Speaker diarization	No
Word-level timestamps	No
Streaming / real-time	No
Languages supported	None
HIPAA eligible	No

Pipecat vs Whipscribe

Feature	Pipecat	Whipscribe
Category	Open source	Transcription APIs
Pricing	free	free beta
Speaker diarization	—	Yes
Word timestamps	—	Yes
Streaming	—	No
Languages	—	99
Platforms	Linux, macOS, Windows, Cloud	Web, API, MCP

Alternatives to Pipecat

OpenAI Whisper

OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k

whisper.cpp

Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k

faster-whisper

SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.