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.| Service | Setup | Maintainer |
|---|---|---|
| Finchvox | uv add finchvox | Community |
| Future AGI | uv add traceAI-pipecat | Community |
| OpenInference | uv add openinference-instrumentation-pipecat | Community |
| Roark | uv add pipecat-roark | Community |
| Sentry | uv add "pipecat-ai[sentry]" | Pipecat |
Audio Filters
Audio filters reduce background noise and isolate the speaker’s voice in the input audio stream.| Service | Setup | Maintainer |
|---|---|---|
| ai-coustics | uv add "pipecat-ai[aic]" | Pipecat |
| Koala | uv add "pipecat-ai[koala]" | Pipecat |
| Krisp VIVA | uv add "pipecat-ai[krisp]" | Pipecat |
| RNNoise | uv add "pipecat-ai[rnnoise]" | Pipecat |
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.| Service | Setup | Maintainer |
|---|---|---|
| Moss | uv add pipecat-moss | Community |
Large Language Models
LLMs receive text or audio based input and output a streaming text response.| Service | Setup | Maintainer |
|---|---|---|
| Anannas AI | uv add pipecat-anannas | Community |
| Anthropic | uv add "pipecat-ai[anthropic]" | Pipecat |
| AWS Bedrock | uv add "pipecat-ai[aws]" | Pipecat |
| Azure | uv add "pipecat-ai[azure]" | Pipecat |
| Cerebras | uv add "pipecat-ai[cerebras]" | Pipecat |
| DeepSeek | uv add "pipecat-ai[deepseek]" | Pipecat |
| Fireworks AI | uv add "pipecat-ai[fireworks]" | Pipecat |
| Google Gemini | uv add "pipecat-ai[google]" | Pipecat |
| Google Vertex AI | uv add "pipecat-ai[google]" | Pipecat |
| Grok | uv add "pipecat-ai[grok]" | Pipecat |
| Groq | uv add "pipecat-ai[groq]" | Pipecat |
| Inception | uv add "pipecat-ai[inception]" | Pipecat |
| Mistral | uv add "pipecat-ai[mistral]" | Pipecat |
| Nebius | uv add "pipecat-ai[nebius]" | Pipecat |
| Novita AI | uv add "pipecat-ai[novita]" | Pipecat |
| NVIDIA | uv add "pipecat-ai[nvidia]" | Pipecat |
| Ollama | uv add "pipecat-ai[ollama]" | Pipecat |
| OpenAI | uv add "pipecat-ai[openai]" | Pipecat |
| OpenAI Responses | uv add "pipecat-ai[openai]" | Pipecat |
| OpenRouter | uv add "pipecat-ai[openrouter]" | Pipecat |
| Perplexity | uv add "pipecat-ai[perplexity]" | Pipecat |
| Qwen | uv add "pipecat-ai[qwen]" | Pipecat |
| SambaNova | uv add "pipecat-ai[sambanova]" | Pipecat |
| Sarvam | uv add "pipecat-ai[sarvam]" | Pipecat |
| Simplismart | uv pip install git+https://github.com/simpli-smart/pipecat-simplismart.git | Community |
| Together AI | uv add "pipecat-ai[together]" | Pipecat |
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.| Service | Setup | Maintainer |
|---|---|---|
| AWS Nova Sonic | uv add "pipecat-ai[aws-nova-sonic]" | Pipecat |
| Gemini Live | uv add "pipecat-ai[google]" | Pipecat |
| Gemini Live Vertex AI | uv add "pipecat-ai[google]" | Pipecat |
| Grok Voice Agent | uv add "pipecat-ai[grok]" | Pipecat |
| Inworld Realtime | uv add "pipecat-ai[inworld]" | Pipecat |
| OpenAI Realtime | uv add "pipecat-ai[openai]" | Pipecat |
| Ultravox | uv add "pipecat-ai[ultravox]" | Pipecat |
Serializers
Serializers convert between frames and media streams, enabling real-time communication over a websocket.| Service | Setup | Maintainer |
|---|---|---|
| Asterisk | uv add pipecat-asterisk | Community |
| AwaazAI | uv add pipecat-awaazai | Community |
| Bandwidth | uv add pipecat-bandwidth | Community |
| Exotel | Built in | Pipecat |
| Genesys | Built in | Pipecat |
| Plivo | Built in | Pipecat |
| Telnyx | Built in | Pipecat |
| Twilio | Built in | Pipecat |
| Vonage | Built in | Pipecat |
| Wavix | uv add pipecat-wavix | Community |
Speech-to-Text
Speech-to-Text services receive and audio input and output transcriptions.| Service | Setup | Maintainer |
|---|---|---|
| AssemblyAI | uv add "pipecat-ai[assemblyai]" | Pipecat |
| AWS Transcribe | uv add "pipecat-ai[aws]" | Pipecat |
| Azure | uv add "pipecat-ai[azure]" | Pipecat |
| Cartesia | uv add "pipecat-ai[cartesia]" | Pipecat |
| Deepgram | uv add "pipecat-ai[deepgram]" | Pipecat |
| ElevenLabs | uv add "pipecat-ai[elevenlabs]" | Pipecat |
| Fal Wizper | uv add "pipecat-ai[fal]" | Pipecat |
| Gladia | uv add "pipecat-ai[gladia]" | Pipecat |
uv add "pipecat-ai[google]" | Pipecat | |
| Gradium | uv add "pipecat-ai[gradium]" | Pipecat |
| Groq (Whisper) | uv add "pipecat-ai[groq]" | Pipecat |
| Mistral | uv add "pipecat-ai[mistral]" | Pipecat |
| Moonshine | uv add "pipecat-ai[moonshine]" | Pipecat |
| NVIDIA | uv add "pipecat-ai[nvidia]" | Pipecat |
| OpenAI | uv add "pipecat-ai[openai]" | Pipecat |
| Ringg AI | uv pip install git+https://github.com/Stonkr/pipecat-ringg.git | Community |
| Sarvam | uv add "pipecat-ai[sarvam]" | Pipecat |
| Simplismart | uv pip install git+https://github.com/simpli-smart/pipecat-simplismart.git | Community |
| SLNG | uv add pipecat-slng | Community |
| Smallest | uv add "pipecat-ai[smallest]" | Pipecat |
| Soniox | uv add "pipecat-ai[soniox]" | Pipecat |
| Speechmatics | uv add "pipecat-ai[speechmatics]" | Pipecat |
| Uplift AI | uv pip install git+https://github.com/havkerboi123/pipecat-upliftai-stt.git | Community |
| Whisper | uv add "pipecat-ai[whisper]" | Pipecat |
| xAI | uv add "pipecat-ai[xai]" | Pipecat |
Text-to-Speech
Text-to-Speech services receive text input and output audio streams or chunks.| Service | Setup | Maintainer |
|---|---|---|
| Async | uv add "pipecat-ai[asyncai]" | Pipecat |
| AWS Polly | uv add "pipecat-ai[aws]" | Pipecat |
| Azure | uv add "pipecat-ai[azure]" | Pipecat |
| Camb AI | uv add "pipecat-ai[camb]" | Pipecat |
| Cartesia | uv add "pipecat-ai[cartesia]" | Pipecat |
| Deepdub | uv add pipecat-deepdub-tts | Community |
| Deepgram | uv add "pipecat-ai[deepgram]" | Pipecat |
| ElevenLabs | uv add "pipecat-ai[elevenlabs]" | Pipecat |
| Fish | uv add "pipecat-ai[fish]" | Pipecat |
uv add "pipecat-ai[google]" | Pipecat | |
| Gradium | uv add "pipecat-ai[gradium]" | Pipecat |
| Groq | uv add "pipecat-ai[groq]" | Pipecat |
| Hume | uv add "pipecat-ai[hume]" | Pipecat |
| Inworld | Built in | Pipecat |
| Kokoro | uv add "pipecat-ai[kokoro]" | Pipecat |
| LMNT | uv add "pipecat-ai[lmnt]" | Pipecat |
| Lokutor | uv add pipecat-lokutor | Community |
| MiniMax | Built in | Pipecat |
| Mistral | uv add "pipecat-ai[mistral]" | Pipecat |
| Murf AI | uv add pipecat-murf-tts | Community |
| Neuphonic | uv add "pipecat-ai[neuphonic]" | Pipecat |
| NVIDIA | uv add "pipecat-ai[nvidia]" | Pipecat |
| OpenAI | uv add "pipecat-ai[openai]" | Pipecat |
| Pipecat TTS Cache | uv add pipecat-tts-cache | Community |
| Piper | Built in | Pipecat |
| ResembleAI | uv add "pipecat-ai[resemble]" | Pipecat |
| Respeecher | uv add pipecat-respeecher | Community |
| Rime | uv add "pipecat-ai[rime]" | Pipecat |
| Rumik AI | uv add pipecat-rumik | Community |
| Sarvam | Built in | Pipecat |
| Simplismart | uv pip install git+https://github.com/simpli-smart/pipecat-simplismart.git | Community |
| SLNG | uv add pipecat-slng | Community |
| Smallest AI | uv add "pipecat-ai[smallest]" | Pipecat |
| Soniox | uv add "pipecat-ai[soniox]" | Pipecat |
| Speechmatics | uv add "pipecat-ai[speechmatics]" | Pipecat |
| Supertonic | uv add pipecat-supertonic | Community |
| Typecast | uv add pipecat-ai-typecast | Community |
| Uplift AI | uv pip install git+https://github.com/havkerboi123/pipecat-upliftai-tts.git | Community |
| Voice.ai | uv pip install git+https://github.com/voice-ai/voice-ai-pipecat-tts.git | Community |
| xAI | uv add "pipecat-ai[xai]" | Pipecat |
| XTTS | uv add "pipecat-ai[xtts]" | Pipecat |
Translation
Translation services enable real-time speech-to-speech and speech-to-text translation.| Service | Setup | Maintainer |
|---|---|---|
| Pinch | uv add pipecat-plugins-pinch | Community |
Transports
Transports exchange audio and video streams between the user and bot.| Service | Setup | Maintainer |
|---|---|---|
| BeyTransport | pip install pipecat-ai-bey | Community |
| DailyTransport | uv add "pipecat-ai[daily]" | Pipecat |
| FastAPIWebSocketTransport | uv add "pipecat-ai[websocket]" | Pipecat |
| HeyGenTransport | uv add "pipecat-ai[heygen]" | Pipecat |
| LemonSliceTransport | uv add "pipecat-ai[lemonslice]" | Pipecat |
| LiveKitTransport | uv add "pipecat-ai[livekit]" | Pipecat |
| SmallWebRTCTransport | uv add "pipecat-ai[webrtc]" | Pipecat |
| TavusTransport | uv add "pipecat-ai[tavus]" | Pipecat |
| VonageVideoConnectorTransport | uv add "pipecat-ai[vonage-video-connector]" | Pipecat |
| WebSocket Transports | uv add "pipecat-ai[websocket]" | Pipecat |
| WhatsAppTransport | uv add "pipecat-ai[webrtc]" | Pipecat |
Turn Detection
Turn detection models decide when the user has finished speaking.| Service | Setup | Maintainer |
|---|---|---|
| Krisp VIVA Turn | uv add "pipecat-ai[krisp]" | Pipecat |
| Smart Turn | Built in | Pipecat |
VAD
VAD services analyze audio input to detect when a user starts and stops speaking.| Service | Setup | Maintainer |
|---|---|---|
| ai-coustics Quail | uv add "pipecat-ai[aic]" | Pipecat |
| FIRE RED VAD | uv add pipecat-firered-vad | Community |
| Krisp VIVA | uv add "pipecat-ai[krisp]" | Pipecat |
| Silero | Built in | Pipecat |
| TEN VAD | pip install pipecat-ten-vad | Community |