Pipecat
Pipecat is an open-source Python framework under BSD-2-Clause, maintained by Daily, for building real-time voice and multimodal conversational agents. It wires a speech-to-text service, a language model and a text-to-speech service into a live conversation over WebRTC, WebSocket or a phone line, with the widest provider list on this site, including local Whisper, Ollama, Kokoro and Piper, and telephony serialisers for six carriers.
What does Pipecat do?
Pipecat "is an open-source Python framework for building real-time voice and multimodal conversational agents". You build a pipeline out of a speech-to-text service, a language model and a text-to-speech service, and the framework moves audio and text between them in real time.
The README's provider lists are long. Speech to text: 23 services, including local Whisper and Moonshine. Language models: 25, including Ollama for local use. Text to speech: 32, including Kokoro, Piper and XTTS locally and ElevenLabs, Cartesia and others hosted. Speech-to-speech models from AWS, Google, OpenAI, xAI and Ultravox. Transports: Daily, LiveKit, SmallWebRTC, Vonage, WebSocket, FastAPI WebSocket, WhatsApp and a local transport. Telephony serialisers: Exotel, Genesys, Plivo, Twilio, Telnyx and Vonage. Pipelines compose: "Each pipeline is an agent. Compose them with handoff, parallel fan-out, sidecar workers, or distributed deployments." Voice activity detection uses Silero, with noise reduction from several vendors.
Key facts
- Licence: BSD-2-Clause, copyright Daily, with no added conditions.
- Speech-to-text providers listed: 23, including AssemblyAI, Deepgram, ElevenLabs, Google, OpenAI, and local Whisper and Moonshine.
- Language model providers listed: 25, including Anthropic, Google, OpenAI, and Ollama for local models.
- Text-to-speech providers listed: 32, including ElevenLabs, Cartesia, Kokoro, Piper and XTTS.
- Speech-to-speech models from AWS, Google, OpenAI, xAI and Ultravox.
- Transports: Daily, LiveKit, SmallWebRTC, Vonage, WebSocket, FastAPI WebSocket, WhatsApp and a local transport; telephony serialisers for Exotel, Genesys, Plivo, Twilio, Telnyx and Vonage.
- Pipelines compose: "Each pipeline is an agent. Compose them with handoff, parallel fan-out, sidecar workers, or distributed deployments."
- Install with pip install pipecat-ai or uv, providers as extras; Python 3.11 minimum, 3.12 recommended; the CLI scaffolds a phone or web bot and can deploy to Pipecat Cloud.
What does it replace, and where does it fall short?
Pipecat replaces Vapi, Retell AI and ElevenLabs Agents as the layer that wires a live voice conversation together, over the web or a phone line, with every model chosen by you. Its licence is BSD-2-Clause with no added conditions.
Where it falls short: it is a framework, so the speech models, the language model, the phone carrier and the hosting are separate accounts and separate bills. Interruption handling is not described in the README beyond voice activity detection. Daily, the maintainer, sells Pipecat Cloud and enterprise support.
How does Pipecat run?
pip install pipecat-ai or uv add pipecat-ai, with providers added as extras; the CLI (pipecat init) scaffolds "a new phone or web/mobile bot" and can deploy to Pipecat Cloud. "Run Pipecat on your local machine, then move your agent processes to the cloud when you're ready." Python 3.11 minimum, 3.12 recommended. Some extras need system libraries.
Who is Pipecat for?
A team that wants to choose every component of a voice agent and may change any of them later. A team that wants the media server open source too should compare LiveKit Agents.
What limits does the README state?
"Only the core framework is included by default." The local and gstreamer extras "require system dependencies".
Questions people ask
Is Pipecat open source?
Yes. Pipecat is BSD-2-Clause with no added conditions, an OSI approved licence. Daily, which maintains it, sells Pipecat Cloud hosting and enterprise support, and neither is required to run the framework.
Does Pipecat require Daily's service?
No. Daily is one of eight transports listed in the README, alongside LiveKit, SmallWebRTC, Vonage, WebSocket, FastAPI WebSocket, WhatsApp and a local transport. The README says to run Pipecat on your local machine and move to the cloud when you are ready.
Can Pipecat make and receive phone calls?
Yes. Telephony serialisers are listed for Exotel, Genesys, Plivo, Twilio, Telnyx and Vonage, and the CLI scaffolds a phone bot from a template. The phone number and the carrier account are yours to set up.
How does Pipecat compare with Vapi and Retell?
Pipecat gives you the pipeline with every model chosen by you, local or hosted, and no platform fee, at the cost of running it. Vapi and Retell give you a dashboard, a number and a bill. The alternatives to Vapi and alternatives to Retell AI pages compare the four frameworks.
Which models can run locally with Pipecat?
From its README lists: Whisper and Moonshine for speech to text, Ollama for the language model, and Kokoro, Piper and XTTS for text to speech, all of which run on your own hardware. Silero provides voice activity detection.
Sources
- Pipecat README and BSD-2-Clause LICENSE: github.com/pipecat-ai/pipecat, read 2026-09-16.
Compared with the others
On the open-source alternatives to Vapi page, Pipecat is the pick for the widest provider and carrier list. BSD-2-Clause, maintained by Daily. Over twenty speech-to-text and language providers, over thirty voices including local Whisper, Ollama, Kokoro and Piper, and telephony serialisers for Twilio, Telnyx, Plivo, Vonage, Exotel and Genesys.
Also on that page: LiveKit Agents for the whole stack on your own servers, TEN Framework for a visual designer, if agora fits, Bolna for a phone agent from a json file.
On the open-source alternatives to Retell AI page, Pipecat is the pick for the widest provider and carrier list. BSD-2-Clause, maintained by Daily. Over twenty speech-to-text and language providers, over thirty voices including local Whisper, Ollama, Kokoro and Piper, and telephony serialisers for Twilio, Telnyx, Plivo, Vonage, Exotel and Genesys.
Also on that page: LiveKit Agents for the whole stack on your own servers, TEN Framework for a visual designer, if agora fits, Bolna for a phone agent from a json file.
On the open-source alternatives to ElevenLabs Agents page, Pipecat is the pick for the widest provider and carrier list. BSD-2-Clause, maintained by Daily. Over twenty speech-to-text and language providers, over thirty voices including local Whisper, Ollama, Kokoro and Piper, and telephony serialisers for Twilio, Telnyx, Plivo, Vonage, Exotel and Genesys.
Also on that page: LiveKit Agents for the whole stack on your own servers, TEN Framework for a visual designer, if agora fits.
More voice agent frameworks
An Apache-2.0 framework for real-time voice agents that connects any speech, language and voice provider, with semantic turn detection, native MCP tool support, a test framework, and an open-source media and SIP stack it can run on entirely.
A real-time conversational AI framework from Agora with a visual designer, a SIP extension and turn detection, released under Apache-2.0 plus conditions that forbid competing deployments, which makes it source available rather than open source.
Added September 16, 2026. Every claim above comes from the project's README, LICENSE or model card, read on September 16, 2026, or from the GitHub API on the date shown in the panel. Found an error? Write to reveneau@licheo.com and it is fixed in the next weekly pass. Repository: github.com/pipecat-ai/pipecat.
Want Pipecat running on your own servers?
Reveneau sets it up on your hardware, connects it to your product, and builds the software around it.