Human-friendly voice AI that keeps customers from shouting "live agent!"
Easily integrate voice AI into your stack for smooth, personalized customer conversations — no complicated infrastructure or awkward AI moments.
Our scalable solution combines fast speech-to-text (STT) and text-to-speech (TTS) capabilities with the AI of your choice, seamlessly orchestrated through a WebSocket API.
-
Avoid long pauses or waiting for voice AI to finish
Cure awkward digital pauses with Deepgram Flux, automatic language detection, and SSML tags. Low latency keeps the conversation flowing for far less robotic conversations.
-
Deliver natural voice, pacing, and intonation
Provide customer interactions that sound like a real person, with the option to seamlessly transfer to a live agent for complex issues.
-
Add context for personalized support
Enable smooth input/output with your large language model (LLM) so your AI agent can recognize customers and recall interactions.
Built for live conversation
median latency
at the 95th percentile*
Deliver effortless self-service support
Enable context-aware, intelligent virtual agents that handle inquiries efficiently—and know exactly when to bring in a human.
-
Handle routine inquiries while keeping customers engaged and frustration-free.
-
Escalate complex or sensitive issues to live agents when needed.
-
Orchestrate customer data to provide personalized, context-rich interactions at scale.
Conversation Relay features
New
Turn every interaction into a continuous, contextual conversation
Conversation Relay is part of the Conversations layer of the Twilio platform. You can turn fragmented customer interactions into a continuous conversation that moves across channels, AI agents and human agents and time without losing any context. In fact, it gets smarter with every interaction through a persistent customer memory.
-
LLM integration that works for you
Get the flexibility to bring your own LLM so you can control your UX, manage costs, and adopt new tech as it's released.
-
Speech recognition STT
Convert spoken words into text in real time to supply your LLM with accurate transcription for responsive conversations.
-
Natural human-sounding TTS
Get pronunciation, intonation, and rhythm right, or bring your own Text-to-Speech capabilities for a custom integration.
-
Interruption handling
Use adjustable interruption sensitivity to fine-tune exactly how the agent reacts in noisy environments.
-
Global connectivity
Access flexible, secure connectivity that includes number provisioning porting compliance.
-
Low-latency infrastructure
Minimize latency to improve the quality of voice AI interactions and ensure a better customer experience.
-
Scale securely in highly regulated industries
Build PCI-compliant workflows and HIPAA-eligible architectures to deploy compliant solutions faster.
Start bringing your voice AI agent to life
Explore our comprehensive APIs, documentation, and the Conversation Relay Studio Widget, which allows teams to deploy secure AI voice flows using drag-and-drop tools.
Your AI powers the conversations. We handle the voice.
Deploy secure voice AI flows using our intuitive drag-and-drop Studio Widget or comprehensive APIs, so you can focus on designing the smart, meaningful interactions your virtual agents need to deliver.
Customers often face:
- High Complexity: Managing real-time communications, websockets, and codecs.
- Latency Issues: Balancing performance with user experience.
- Integration Pain Points: Orchestrating TTS, STT, and LLM solutions while maintaining scalability.
Conversation Relay addresses these issues with a streamlined, ready-to-use infrastructure that minimizes technical barriers.
Latency directly impacts the quality of voice AI interactions. High latency causes unnatural pauses and disruptions, which can frustrate customers and undermine trust. Conversation Relay is optimized to minimize latency, ensuring smooth, human-friendly conversations that are critical for high-stakes interactions in customer support and sales.
- Best-of-breed providers integrated natively with the Twilio platform
- Dedicated, single-tenant, customized infrastructure colocated with call and media edges.
- Proprietary orchestration algorithms for handling interruptions, prefetching results, and batching text tokens.
Conversation Relay is a conversational AI product offering designed to make building production-quality voice AI agents easy. It simplifies the development process by integrating key components like Speech-to-Text (STT), Text-to-Speech (TTS), and Large Language Model (LLM) orchestration. Unlike Media Streams, which requires customers to manage their own media servers, orchestration, and integrations, Conversation Relay provides a ready-to-use websocket interface with lower latency and greater control, making it easier to build and scale voice AI solutions.
Text-to-Speech Providers
- Google Voices
- Amazon Voice
- ElevenLabs Voices
Automated Speech Recognition
- Google Speech API
- Amazon Speech
- DeepGram
Conversation Relay provides pre-configured packages and APIs that simplify the setup process, allowing customers to focus on their AI models and user experiences instead of dealing with the underlying infrastructure. These quickstart configurations are tailored to common use cases, enabling faster time-to-value.
It depends on which provider options are selected.
- Regionalized: Amazon, Google
- US1: Deepgram