GA Daily

Pipecat + Pipecat Cloud

Pipecat is an open-source (BSD-2-Clause) Python framework for voice and multimodal agents with roughly 85 STT/LLM/TTS integrations; Pipecat Cloud is Daily's hosting service for Pipecat agents with Daily WebRTC and telephony built in.

Est. per minute$0.03 - 0.10

Overview

Best for: Python teams that want maximum provider choice and open-source portability, with optional managed hosting.

At a glance

Platform $/min$0.01
All-in priceNo
Entry plan $/mo$0
Free tierYes
Phone numbersYes
Own LLMYes
Own keysYes
RecordingYes
Noise cancelYes
Smart turnsYes
WebRTCYes
WebSocketYes
Phone / SIPYes
Self-hostYes
Open weightsYes

Fee is agent-1x hosting ($0.02 / $0.03 for larger sizes); open-source Pipecat is free to self-host. Pricing page says unlimited concurrency. No explicit free credit amount.

Audio in

Daily WebRTC (Opus), WebSocket serializers for Twilio/Telnyx/Plivo/Vonage (8 kHz mu-law or PCM)

Audio out

Same as input

Languages

Depends on chosen providers.

Latency

No vendor number verified.

Regions

Not verified in this research.

Compliance

Not verified in this research for Pipecat Cloud (ask Daily for SOC 2/HIPAA terms).

Features

  • turn detection (Smart Turn open model, Silero VAD)
  • noise cancellation (Krisp VIVA)
  • telephony (Daily SIP/PSTN, Twilio and others via WebSocket)
  • multi-provider plug-ins (~85 services)
  • recording
  • metrics
  • reserved warm instances
  • speech-to-speech services

Pricing

WhatPriceUnitNotes
Agent hosting agent-1x$0.01per active minuteCompute only; LLM/STT/TTS billed by your providers (bring your own keys).
Reserved (always-on) agent-1x$0.0005per reserved minuteBilled every minute until you turn it off; avoids cold starts.
Daily WebRTC voice (1:1 on Pipecat Cloud)$0.001 listed, marked Freeper minutePage labels 1:1 voice sessions free; voice+video $0.004/participant minute.
Daily PSTN dial-in/out (SIP included)$0.018per minuteTranscoding adds charges.
Daily SIP dial-in/out$0.003-$0.02per minute
SIP REFER transfer$0.20per eventMinutes keep accruing until the handoff completes.
Krisp VIVA noise cancellationFree to 10k min, then $0.0015per minutePer month.
Recording (audio only)$0.005per minuteStorage $0.003/min.
How the per-minute estimate was worked out

$0.01 agent-1x hosting + ~$0.005-0.01 STT + ~$0.002-0.02 LLM + ~$0.015-0.05 TTS (provider list prices, billed by providers) + $0 for 1:1 WebRTC or $0.018 for Daily PSTN. Not a vendor figure; it is an assembly of the listed rates with typical provider prices.

Free tier: Page says 'Start building for free'; 1:1 Daily WebRTC voice labelled free; Krisp free up to 10k min/month. No explicit credit amount found.

Source: daily.co

Setup

  1. Python 3.11+ and uv. Get Deepgram, OpenAI and Cartesia keys (quickstart stack).
  2. Run the quickstart bot locally with 'uv run bot.py' and open the local WebRTC client.
  3. Install the CLI: uv tool install "pipecat-ai[cli]"; then 'pipecat cloud auth login'.
  4. 'pipecat cloud secrets set <secret-set> --file .env', configure pcc-deploy.toml (agent_name, secret_set, scaling.min_agents), then 'pipecat cloud deploy' (cloud build, no registry needed).
  5. Start sessions via the REST API or Python SDK; attach Daily phone numbers or SIP for calls.

Endpoint

Pipecat Cloud REST API / Daily rooms

Authentication

Pipecat Cloud API key (CLI login); provider keys stored as secret sets

Quick start python

# Core of the Pipecat quickstart bot.py (Oct 2026). Imports omitted: copy them from
# docs.pipecat.ai quickstart, class names changed in recent releases
# (PipelineTask/PipelineRunner -> PipelineWorker/WorkerRunner).
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = CartesiaTTSService(api_key=os.getenv("CARTESIA_API_KEY"),
    settings=CartesiaTTSService.Settings(voice=os.getenv("CARTESIA_VOICE_ID")))
llm = OpenAIResponsesLLMService(api_key=os.getenv("OPENAI_API_KEY"),
    settings=OpenAIResponsesLLMService.Settings(model="gpt-4.1",
        system_instruction="You are a brief, friendly voice assistant."))

context = LLMContext()
user_agg, assistant_agg = LLMContextAggregatorPair(
    context, user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()))

pipeline = Pipeline([transport.input(), stt, user_agg, llm, tts,
                     transport.output(), assistant_agg])
worker = PipelineWorker(pipeline, params=PipelineParams(enable_metrics=True))
runner = WorkerRunner(handle_sigint=runner_args.handle_sigint)
await runner.add_workers(worker)
await runner.run()

# Deploy: pipecat cloud auth login
#         pipecat cloud secrets set my-secrets --file .env
#         pipecat cloud deploy

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Hosting price excludes all AI models

Pipecat Cloud bills compute and Daily transport only; you pay Deepgram/OpenAI/Cartesia (or others) directly. Bundled inference billing exists only for enterprise via sales.

Reserved instances bill around the clock

Warm 'reserved' agents avoid cold starts but bill every minute until switched off ($0.0005/min for agent-1x is about $21.60 per 30-day month per instance).

SIP transfers keep the meter running

With SIP REFER the call stays anchored to Daily until the handoff completes, then a $0.20 event fee applies.

Fast-moving API

Class names and the CLI changed in 2025-2026 (pcc -> 'pipecat cloud', PipelineTask -> PipelineWorker). Pin the pipecat-ai version and follow the docs for your version.

Telephony audio via WebSocket is 8 kHz

When using Twilio/Telnyx/Plivo serializers, audio is usually 8 kHz mu-law; configure sample rates correctly in the transport params.

Plus 12 warnings that apply to all platforms and telephony APIs. See category warnings.

Limits

  • Pricing page says 'unlimited concurrency'
  • Cold starts unless you keep min_agents / reserved instances warm

Models and products

NameStatusNotes
Pipecat (open source)GASelf-run anywhere; transports include Daily, LiveKit, SmallWebRTC, FastAPI/WebSocket, Vonage, WhatsApp.
Pipecat Cloud agent-1xGA0.5 vCPU, 1 GB: $0.01/min active, $0.0005/min reserved.
Pipecat Cloud agent-2xGA1 vCPU, 2 GB: $0.02/min active, $0.001/min reserved.
Pipecat Cloud agent-3xGA1.5 vCPU, 3 GB: $0.03/min active, $0.0015/min reserved.

Docs and sources

Docs

Sources used

Not fully verified

Regions, compliance attestations, free credit amount; snippet imports deliberately omitted because module paths changed in recent releases.

Similar platforms APIs

Spotted a wrong price or a dead link?