Daily.co Bots and the Pipecat Cloud Migration: Telephony for AI Agents in 2026

Daily.co launched Daily Bots in 2024 as the open-source cloud for voice agents. By July 2025 it was deprecated in favor of Pipecat Cloud, which went GA in January 2026. The migration kept the good parts: native Twilio Voice integration, Krisp VIVA noise reduction, Daily's WebRTC transport. The new platform is more flexible, deeper to customize, and meaningfully cheaper.

Background

Daily.co is a WebRTC infrastructure company that pivoted toward voice AI in 2023-2024. They built Pipecat as an open-source Python framework for voice and multimodal pipelines, and Daily Bots as a managed cloud for hosting Pipecat agents. The architectural insight was good: standardize on Pipecat's frame-based pipeline, layer Daily's WebRTC infrastructure underneath, sell hosted runtime.

July 2025 Daily Bots was deprecated and customers migrated to Pipecat Cloud, which became the new managed runtime. GA was January 2026. Pipecat Cloud is vendor-neutral (works with any LLM, STT, TTS), supports direct Twilio Voice integration, and bundles Krisp VIVA noise reduction. Pricing is consumption-based per minute of agent runtime.

Architecture

graph LR
    A[PSTN Caller] --> B[Twilio Voice]
    B -->|TwiML Stream| C[Pipecat Cloud]
    C --> D[Krisp VIVA Noise Reduction]
    D --> E[STT - Deepgram or AssemblyAI]
    E --> F[LLM - OpenAI / Anthropic / Gemini]
    F --> G[TTS - ElevenLabs or Cartesia]
    G --> C
    C -->|Daily WebRTC or Twilio Stream| B
    B --> A

# Pipecat agent for Twilio dial-in
from pipecat.pipeline.pipeline import Pipeline
from pipecat.transports.network.twilio_websocket import TwilioWebsocketTransport
from pipecat.services.deepgram import DeepgramSTTService
from pipecat.services.openai import OpenAILLMService
from pipecat.services.cartesia import CartesiaTTSService

transport = TwilioWebsocketTransport(websocket=ws)
pipeline = Pipeline([
    transport.input(),
    DeepgramSTTService(api_key=DG_KEY),
    OpenAILLMService(api_key=OAI_KEY, model="gpt-4o-realtime"),
    CartesiaTTSService(api_key=CT_KEY, voice_id="...."),
    transport.output()
])

CallSphere implementation

CallSphere terminates every call on Twilio across all six verticals (Healthcare AI on FastAPI :8084 to OpenAI Realtime, Real Estate AI, Sales Calling AI with 5 concurrent outbound, Salon AI, IT Helpdesk AI, After-Hours AI with Twilio simul call+SMS 120-second timeout). 37 agents, 90+ tools, 115+ DB tables, HIPAA + SOC 2, $149/$499/$1499 plans, 14-day trial, 22% affiliate. We use the Twilio Streams primitive directly without Pipecat in production because we needed deeper control over barge-in and tool-call orchestration than the Pipecat pipeline gives. For prospects in early stage (under 50 calls/day) we recommend Pipecat Cloud as a path of least resistance to a working Twilio + AI deployment, and offer migration tooling that lifts conversation history into our richer 115+ table schema once they outgrow it.

Build steps

1. Sign up for Pipecat Cloud, install the pipecat CLI and pipecat-cloud Python package.
2. Write your agent as a Pipecat Pipeline with the Twilio WebSocket transport.
3. Test locally with the quickstart-phone-bot template against a Twilio number.
4. Deploy to Pipecat Cloud: pipecat-cloud deploy ./agent.py; the platform builds a container and exposes a WebSocket URL.
5. Configure your Twilio number's TwiML response to at the Pipecat Cloud URL.
6. Enable Krisp VIVA in the agent config for noise reduction.
7. Monitor via Pipecat Cloud dashboard; metrics include latency, frame count, error rate.

Pitfalls

• Pipecat versioning moves fast; pin the pipecat package version in requirements.txt.
• Twilio mulaw 8 kHz is the default transport; for OpenAI Realtime with Opus you transcode inside the pipeline.
• Krisp VIVA is opt-in and adds ~10 ms latency; worth it on noisy calls.
• Pipecat Cloud is multi-region but room SDP negotiation is region-bound; a US caller hitting an EU agent adds 70 ms.
• The deprecation of Daily Bots is complete; old agent definitions need migration before October 2026 cutoff.

FAQ

Pipecat Cloud or self-host Pipecat? Cloud for sub-100 concurrent agents and small teams. Self-host on Kubernetes when you need custom GPU placements or strict compliance.

Native Twilio integration cost? Pipecat Cloud bills per minute of agent runtime; Twilio bills per minute of voice. Combined ~2-3x base voice cost in 2026.

HIPAA? Pipecat Cloud offers BAAs on enterprise tier; underlying Daily and Twilio are also BAA-eligible.

Multimodal support? Yes, Pipecat is voice-and-vision capable. Useful for video kiosk agents, less for pure phone.

Can I migrate from Daily Bots automatically? Daily provides a migration script; manual review of agent code is recommended.

Sources

• Pipecat Cloud GA announcement
• Pipecat Twilio WebSocket Integration
• Pipecat quickstart phone bot
• Daily Bots Twilio Voice native integration announcement

Start a 14-day trial of our managed AI voice, see pricing for $149/$499/$1499, or book a demo to compare Pipecat Cloud against our stack.

## How this plays out in production One layer below what *Daily.co Bots and the Pipecat Cloud Migration: Telephony for AI Agents in 2026* covers, the practical question every team hits is multi-turn handoffs between specialist agents without losing slot state, sentiment, or escalation context. Treat this as a voice-first system from the first prompt: the agent's persona, its tool surface, and its escalation rules all flow from that single decision. Teams that ship fast tend to instrument the loop end-to-end before they tune any single component, because the bottleneck is rarely where intuition puts it. ## Voice agent architecture, end to end A production-grade voice stack at CallSphere stitches Twilio Programmable Voice (PSTN ingress, TwiML, bidirectional Media Streams) to a realtime reasoning layer — typically OpenAI Realtime or ElevenLabs Conversational AI — with sub-second response as a hard SLO. Anything north of one second of perceived silence and callers either repeat themselves or hang up; that single number drives the whole architecture. Server-side VAD with proper barge-in support is non-negotiable, otherwise the agent talks over the caller and the conversation collapses. Streaming TTS with phoneme-aligned interruption keeps the cadence natural even when the user changes their mind mid-sentence. Post-call, every transcript is run through a structured pipeline: sentiment, intent classification, lead score, escalation flag, and a normalized slot extraction (name, callback number, reason, urgency). For healthcare workloads, the BAA-covered storage path, audit logs, encryption-at-rest, and PHI-safe transcript redaction are wired in from day one, not bolted on at compliance review. The end state is a system where every call produces a row of structured data, not just a recording. ## FAQ **How do you actually ship a voice agent the way *Daily.co Bots and the Pipecat Cloud Migration: Telephony for AI Agents in 2026* describes?** Treat the architecture in this post as a starting point and instrument it before you tune it. The metrics that matter most early on are end-to-end latency (target < 1s for voice, < 3s for chat), barge-in correctness, tool-call success rate, and post-conversation lead score distribution. Optimize whatever the data flags as the bottleneck, not whatever feels slowest in your head. **What are the failure modes of voice agent deployments at scale?** The two failure modes that bite hardest are silent context loss across multi-turn handoffs and tool calls that succeed in dev but get rate-limited in production. Both are solvable with a proper agent backplane that pins state to a session ID, retries with backoff, and writes every tool invocation to an audit log you can replay. **What does the CallSphere outbound sales calling product do that a regular dialer does not?** It uses the ElevenLabs "Sarah" voice, runs up to 5 concurrent outbound calls per operator, and ships with a browser-based dialer that transfers warm calls back to a human in one click. Dispositions, transcripts, and lead scores write back to the CRM automatically. ## See it live Book a 30-minute working session at [calendly.com/sagar-callsphere/new-meeting](https://calendly.com/sagar-callsphere/new-meeting) and bring a real call flow — we will walk it through the live outbound sales dialer at [sales.callsphere.tech](https://sales.callsphere.tech) and show you exactly where the production wiring sits.