Voice Infrastructure

Pipecat

Open-source Python framework for building real-time voice and multimodal AI agents.

Voice InfrastructureActive
View company profile →
websitedocs

speech.dev has not published an operational assessment for this entry yet. Facts below are source-linked where available.

Functional overview

Open-source Python framework for building real-time voice and multimodal AI agents. Pipecat Confirm deployment model (managed vs self-hosted), realtime APIs, and pricing on vendor documentation.

Best fit

Engineering teams that want framework-level control over the audio pipeline, transports, services, and deployment environment.

Watch-outs

  • The framework is not a turnkey hosted phone-agent product by itself.
  • Production readiness depends on the surrounding deployment, transport, observability, and model stack.
Availability and pricing
Regions (vendor buckets)
Not listed
Countries
Not listed
Hosting
Self Hosted, Saas Vendor Cloud
Languages
Not listed
Billing model
Open Source
Public list price
Listed on vendor site

The framework is open source; runtime, model, transport, and Pipecat Cloud costs depend on the deployment choices.

Last verified 2026-05-24 · vendor pricing

Capabilities
Inbound Callsyes
Outbound Callsyes
Web Callingyes
Sip Trunkingno
Phone Numbersno
Human Handoffyes
Tool Callingyes
Workflow Builderno
Analyticsno
Evalsno
Integrations and compliance

Stt

deepgramsonioxopenaiassemblyai

Tts

cartesiaelevenlabsdeepgramopenai

Llm

openaianthropicgoogle-gemini

Telephony

twiliodaily-bots

Client Sdks

javascriptreactreact-nativeswiftkotlinc++
Sources
HomepageDocsOverviewQuickstartGithub