By Sagar Shankaran, Founder of CallSphere
Daily.co Bots deprecated July 2025 and was succeeded by Pipecat Cloud (GA January 2026). The replacement keeps Twilio Voice native integration, Krisp VIVA noise reduction, and Daily WebRTC transport, with deeper customization and lower cost.
Key takeaways
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.
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.
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 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.
pipecat-cloud deploy ./agent.py; the platform builds a container and exposes a WebSocket URL.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.
Hear it before you finish reading
Talk to a live CallSphere AI voice agent in your browser — 60 seconds, no signup.
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.
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.
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.
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.
Still reading? Stop comparing — try CallSphere live.
CallSphere ships complete AI voice agents per industry — 14 tools for healthcare, 10 agents for real estate, 4 specialists for salons. See how it actually handles a call before you book a demo.
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.
Book a 30-minute working session at 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 and show you exactly where the production wiring sits.
Written by
Sagar Shankaran· Founder, CallSphere
Sagar Shankaran is the founder of CallSphere, where he builds production AI voice and chat agents deployed across healthcare, hospitality, real estate, and home services. He writes about agentic AI, LLM engineering, and shipping voice agents that handle real calls in production.
See how AI voice agents work for your industry. Live demo available -- no signup required.
A founder's guide to the female voice generator landscape: AI female voices, Japanese voices, robot voices, and how CallSphere ships 57+ voices live.
A VoIP telephone number is a phone number that routes calls over the internet instead of copper lines. Learn what a VoIP number is, how to get one, what it costs, and how to pair it with an AI voice agent in 2026.
How we built a fault-tolerant HVAC emergency triage and tech-dispatch platform on Kubernetes — three-tier CQRS, 11 micro-agents on the OpenAI Agents SDK + LangGraph, NATS JetStream, DTMF/SMS/WebSocket acceptance, circuit breakers, and an evaluation pipeline that catches regressions before they wake a tech at 3 AM.
MOS 4.3+ is the band where AI voice feels human. Drop below 3.6 and conversations break. Here is how to measure, improve, and alert on MOS in production AI voice using G.711, Opus, and the underlying packet loss / jitter / latency math.
Where every millisecond goes between caller and AI: PSTN, carrier, STT, LLM, TTS, and back. The component-level targets that ship in 2026 and how to hit them.
Voicemail detection accuracy makes or breaks outbound voice AI. CallSphere VoicemailAnalyzerAgent + Twilio AMD vs Vapi defaults. Real call examples included.
© 2026 CallSphere LLC. All rights reserved.