Supported Services

Services marked Pipecat in the Maintainer column ship in the pipecat-ai package and are maintained by the Pipecat team. Services marked Community are community-maintained integrations distributed as separate packages — install them individually and report issues on their source repositories. Categories are listed in alphabetical order.

​

Analytics & Monitoring

Analytics services help you better understand how your service operates.

​

Audio Filters

Audio filters reduce background noise and isolate the speaker’s voice in the input audio stream.

​

Image Generation

Image generation services receive text inputs and output images.

​

Knowledge Retrieval

Knowledge retrieval services enable context-aware search and retrieval of relevant information.

​

Large Language Models

LLMs receive text or audio based input and output a streaming text response.

​

Memory

Memory services can be used to store and retrieve conversations.

​

Realtime LLM

Realtime LLMs (speech-to-speech) are multi-modal models that take in audio, video, or text and output audio or text in real time.

​

Serializers

Serializers convert between frames and media streams, enabling real-time communication over a websocket.

​

Speech-to-Text

Speech-to-Text services receive and audio input and output transcriptions.

​

Text-to-Speech

Text-to-Speech services receive text input and output audio streams or chunks.

​

Translation

Translation services enable real-time speech-to-speech and speech-to-text translation.

​

Transports

Transports exchange audio and video streams between the user and bot.

​

Turn Detection

Turn detection models decide when the user has finished speaking.

​

VAD

VAD services analyze audio input to detect when a user starts and stops speaking.

​

Video

Video services enable you to build an avatar where audio and video are synchronized.

​

Vision

Vision services receive a streaming video input and output text describing the video input.