SpeechStack
Submit a template
Voice AI Stack Library

Every voice AI stack, in one place.

Pick a stack, copy the prompts and configs, ship the agent this week.

Voice Notes

Voice AI recipes, picks, and analysis.

Get the useful new templates plus the occasional teardown of what’s working in production voice AI.

Dental Office ReceptionistInbound AI receptionist for a dental office that checks availability, books, looks up, and cancels appointments through function calls. Uses Deepgram's unified Voice Agent API and Twilio Media Streams, with one-command Fly.io deploy.
new
Drive-Thru Order TakerVoice agent that takes drive-thru orders, manages a structured cart of combos, Happy Meals, à-la-carte items and sauces, and triggers a checkout RPC for a live order-board UI. Includes ambient background audio and an evaluation suite.
new
Healthcare Appointment SchedulerAI voice receptionist for a medical clinic that books, reschedules, and cancels appointments via cal.com, enforces 9–5 business hours, and routes urgent callers to human staff. Ported verbatim from Vapi's official example assistant.
new
Sales Representative with Lead Extraction and Company ResearchA sales voice agent that extracts structured lead information during conversations and performs automated company research. Uses a three-agent architecture with dedicated agents for conversation handling, lead extraction, and company research via web search. Maintains stateful lead accumulation across the conversation.
Doctor Appointment Scheduler with Intake FormA voice agent that guides patients through scheduling doctor appointments by collecting intake information (name, date of birth, reason for visit, contact details) and booking available appointment slots. The agent asks one question at a time, confirms answers, supports editing previous responses, and gracefully handles the entire scheduling workflow.
Outbound Sales Assistant for AirPodsVoice AI agent that conducts outbound sales calls for Apple AirPods, helping customers choose between models by asking qualifying questions about preferences for in-ear vs over-ear and noise canceling features. The agent maintains conversation history, handles interruptions, and can check inventory and place orders through function calls.
Customer Service Agent with Function CallingA voice agent that handles customer service inquiries including order status checks, appointment scheduling, customer information lookup, and conversation management through natural language. Demonstrates production-ready function calling patterns with artificial delays to simulate real-world database operations.
new
Customer Service Agent with Function Calling and Order ManagementA reference implementation demonstrating function calling patterns with voice agents, including customer information lookup, order history retrieval, appointment scheduling, and graceful conversation termination. Built with Flask and WebSockets, it showcases natural conversation flow with agent filler messages and UI-based debugging logs.
new
Space Trading Game with Autonomous Ship AIAn online multiplayer space trading game where players command AI-powered ships that can explore, trade, battle, and collaborate autonomously. The ship agent handles complex multi-tasking including navigation, combat, corporation management, and quest completion through voice or text commands.
new
Telephony voice agent with inbound and outbound call handlingA minimal bridge connecting Twilio Programmable Voice to the AssemblyAI Voice Agent API. Handles both inbound and outbound phone calls with zero audio transcoding by using G.711 μ-law passthrough. Includes tool calling example (generate random number) and automatic barge-in support. Demonstrates how to build a telephony voice agent that answers calls, speaks first on outbound dials, and executes function calls.
new
Outbound Car Sales AgentOutbound AI sales agent that calls a prospect on Twilio and runs a discovery conversation about a new car. Built on ElevenLabs Conversational AI's Twilio bridge; supports dynamic prompts and first messages per call.
new
Tier-1 Support with Warm TransferTier-1 customer support voice agent that resolves common issues and, when escalation is needed, places the customer on hold, dials a supervisor, briefs them with a concise call summary, and bridges all three parties.
new
Phone Bot QuickstartMinimal production-ready Pipecat phone agent that answers inbound Twilio calls via Media Streams. Ships with Deepgram + OpenAI + Cartesia and works as a base template for any voice use case.
new
EdTech Admissions QualifierOutbound voice agent that re-engages prospective bootcamp students who completed a career quiz, answers program and pricing questions, and triggers a HubSpot CRM workflow to book a live demo with the sales team.
new
Candidate Screening InterviewerOutbound voice agent that conducts a structured candidate phone-screen for an hourly-labor marketplace: confirms identity, runs role-specific skill questions, captures structured answers, and approves or rejects the candidate downstream.
new
Real-Time Conversational Voice Bot with Turn DetectionA real-time conversational voice bot that listens through your microphone, transcribes speech, generates intelligent responses, and speaks back with natural turn-taking. Supports both local console mode and browser-based WebRTC sessions. Uses voice activity detection for natural interruption handling.
new
Travel Companion with Location-Based RecommendationsA smart travel assistant that provides personalized recommendations based on your current location. The agent can check the weather, suggest nearby restaurants, provide local news, and share restaurant locations that open directly in Google Maps on iOS devices.
new
Real-Time Voice Assistant with Room-Based ConversationsA voice AI assistant that joins LiveKit rooms and holds natural conversations with participants. The agent automatically greets users, transcribes speech in real-time, generates intelligent responses, and speaks back with natural-sounding voices over WebRTC connections.
Conversational Voice Agent with Tool CallingA conversational voice agent that listens to speech, transcribes it in real-time, processes it through an OpenAI agent with tool-calling support, and speaks the response back. Supports both single-turn demo mode and interactive streaming for continuous conversation.
Elder Care Advisor for Adult ChildrenAn empathy-tuned voice agent that helps adult children explore elder care options for their parents. The agent conducts a conversational assessment covering mobility, health conditions, and care urgency, then provides personalized recommendations and schedules follow-up callbacks. Features a talking-head avatar with real-time lip-sync and structured care summaries.
General Purpose Voice Agent with Low Latency StreamingA low-latency voice agent template demonstrating integration between AssemblyAI's Universal-Streaming API for speech recognition, OpenAI GPT-4 for conversational intelligence, and ElevenLabs for natural voice synthesis. Suitable for building custom voice assistants across various use cases.
Conversational Article Discussion AssistantA fast conversational AI agent that enables users to have natural voice conversations about any article on the web. Built for real-time voice interaction with low latency, it helps users explore and understand web content through dialogue.
IVR Phone Tree with LLM Function CallingAn intelligent phone tree system that replaces traditional IVR menus with conversational AI. Uses LLM function calling and state machines to navigate callers through multi-step interactions, identifying callers and routing them through dynamic conversation paths based on their responses.
Hotel Front Desk Agent with Smart Backchannel FilteringA voice agent that continues speaking through caller backchannels like 'mhm', 'um', and 'yeah' without interrupting, while still responding to real intents. Demonstrates three filtering strategies for handling short utterances during agent speech: STT node override, buffer clearing, and combined approach.
Real-Time Voice Agent with OpenAI and TwilioA custom voice AI agent that integrates OpenAI's Realtime API with Twilio Voice services to enable interactive voice conversations. The agent supports real-time audio streaming, automatic speech detection, response cancellation, and natural conversation flow with interrupt handling. Built with FastAPI and WebSocket communication, it can be configured for sales, support, compliance monitoring, and cold calling applications.
Multi-User Browser Voice Agent with WebRTC TransportA Python worker that bridges LiveKit WebRTC rooms with AssemblyAI's Voice Agent API, enabling multi-user voice conversations with an AI agent in browser, mobile, and desktop clients. The worker handles audio transport while AssemblyAI manages the full AI pipeline including speech-to-text, LLM responses, and text-to-speech with neural turn detection and barge-in support.
PSTN Voice Assistant with Real-Time Transcription and Barge-InA voice assistant that handles inbound and outbound PSTN calls with real-time transcription, supporting barge-in for natural conversation flow. Connects telephony channels to AI voice agents with low-latency streaming and multi-channel support.
Telephony Bridge for Real Time Voice AgentsA telephony server that connects telephony providers like Twilio, Vonage, and Plivo with real-time communication platforms including Pipecat, LiveKit, and Jay.so. Enables seamless call routing, metrics collection, and observability for voice AI deployments. Includes an example taxi dispatcher agent that handles ride bookings and customer inquiries.
Autonomous Incident Manager for Site Reliability EngineeringAn autonomous agent that detects production errors in real time, investigates root causes using AI, generates code patches, and calls on-call engineers via voice to request approval for deployment. Compresses traditional incident response from hours to under 30 seconds.
Insurance Lead Follow-Up AgentAn outbound voice agent that follows up on homeowners insurance quote requests, verifies lead information, gathers property details, and schedules consultations with licensed agents. Features answering machine detection with personalized voicemail delivery.
Multi Provider LLM Proxy for Voice AgentsAn OpenAI-compatible chat completions proxy that enables voice agents to use multiple LLM providers including Amazon Bedrock Agents and OpenAI. Provides an extensible architecture for switching between providers through environment variables or request parameters, supporting both streaming and non-streaming responses with exact OpenAI format matching.
Ecommerce Refund Processing AssistantA voice agent that handles customer refund requests for ecommerce orders. The agent verifies order details, identifies missing items, and processes refunds through an agentic system with human-in-the-loop capabilities for approval workflows.
Flowise AI Voice Agent with Twilio ConversationRelayA customizable voice agent built using Flowise AI's visual flow builder integrated with Twilio ConversationRelay. Supports flexible agent design through Flowise's no-code interface, with example tools for fitness class scheduling including listing classes, booking, cancelling, and finding upcoming reservations.
Autonomous Sales Outbound Calling AgentAn AI-powered sales agent that manages outbound calling campaigns, performs sentiment analysis on conversations, and schedules intelligent follow-ups based on real-time call analysis. The system automates cold calling workflows with conversation enrichment and adaptive scheduling.
Two-Way Conversational Speech AssistantA voice assistant template that enables natural two-way conversations over phone calls using websocket connections to orchestrate real-time audio streaming between callers and AI. Demonstrates interrupt handling and AI preemption capabilities for smooth conversational experiences.
Two Truths and a Lie Interactive Game BotA telephone-based conversational agent that plays the game Two Truths and a Lie with callers. The bot provides three statements over the phone and challenges users to identify which statement is false, creating an engaging interactive entertainment experience.
General Purpose Voice Agent with Open Source NVIDIA ModelsA low-latency voice agent implementation using NVIDIA's open source models (Nemotron Speech ASR, Nemotron-3 Nano LLM, and Magpie TTS). Features adaptive TTS streaming, buffered LLM with 100% KV cache reuse, and multiple deployment options including local GPU execution on DGX Spark/RTX 5090 or cloud deployment via Modal and Pipecat Cloud.
Real-Time Voice Agent with Neural Turn DetectionA production-ready real-time voice agent built with LiveKit Agents framework and AssemblyAI Universal-3 Pro Streaming. Features neural turn detection that distinguishes between mid-sentence pauses and actual end-of-turn signals using acoustic and linguistic cues. Supports mid-session keyterm prompting for domain-specific vocabulary and real-time speaker diarization. Optimized for low-latency conversational experiences with configurable turn detection parameters.
Real Time Multilingual Translation Between Customer and Contact Center AgentA bidirectional voice translation system that enables real-time conversations between customers and contact center agents speaking different languages. The agent intercepts audio from both parties, translates it using OpenAI Realtime API, and delivers the translated audio to the other party. Supports multiple languages including English, Spanish, French, Mandarin, and Hindi through an IVR menu.
Inbound and Outbound Phone Bot with Daily and PlivoA Python-based voice AI agent that handles both inbound and outbound phone calls using Daily for real-time voice streaming and Plivo for telephony. The bot uses Deepgram for speech recognition, GPT-4 for conversation, and Cartesia for text-to-speech, enabling automated phone interactions for customer support, appointment scheduling, or lead qualification.
Voice Agent with Visual Data Verification for Lead CaptureA voice-first AI receptionist that captures user information through natural conversation and ensures 100% data accuracy through a unique human-in-the-loop verification workflow. Users visually confirm all captured information in a form before submission, eliminating transcription errors and ensuring structured data reliability for CRM integration, appointment booking, and lead qualification.
Five Minute Inbound Lead Qualification and TransferA voice agent that automatically calls inbound leads within five minutes of form submission to qualify them and transfer hot prospects to account executives. Research shows calling within five minutes increases close rates by 80 percent, and this agent ensures no lead goes cold while sales teams focus on closing deals.
SaaS Customer Support Agent with AssemblyAIA real-time conversational voice agent that provides customer support for a fictional SaaS product (Acme Cloud). Features smart turn detection using terminal punctuation, barge-in support, and keyterms boosting for domain-specific terminology. Built to handle typical support queries with ultra-low latency and natural conversation flow.
Voicemail Detection Assistant for Outbound CallsAn outbound calling assistant that monitors transcriptions to distinguish between voicemail systems and live humans. When voicemail is detected, it triggers a tool to deliver a pre-recorded message. For live contacts, it delivers a brief message and handles responses professionally before ending the call.
WhatsApp Voice Conversational AgentA voice-based conversational agent that integrates with WhatsApp Business API to handle voice calls over WebRTC. Demonstrates how to build a bot that automatically answers WhatsApp voice calls and conducts natural conversations using Gemini and Pipecat's SmallWebRTC transport.
Customer Support and Appointment Booking AssistantAn intelligent phone assistant that handles real phone conversations for customer support inquiries and appointment scheduling. The agent uses real-time voice streaming to understand caller requests, provide helpful responses, and manage booking workflows through natural multi-turn conversations.
Interactive Voice Game for Discovering Secret CrushesA playful voice AI game where users talk to multiple bot characters to collect clues and discover which character has a crush on them. Built as an interactive quest with WebRTC-based conversational agents, demonstrating gamification of voice AI interactions.
Outbound Call Agent with Voicemail Detection and TransferAn outbound calling agent that initiates phone calls, detects voicemail, looks up availability via function calling, transfers to human operators, and detects intent to end calls. Built with LiveKit SIP and Python Agents Framework, it handles noisy environments with Krisp background voice cancellation.
Web Research Agent with Real-Time Search and Content ExtractionA voice agent that searches the web and extracts page content using the Tavily API, then synthesizes results into conversational responses. Uses Tavily's fast search depth for low-latency voice interactions and deep content extraction for specific pages.
Basic Voice Agent for General ConversationA basic example voice agent that demonstrates real-time conversational AI capabilities using LiveKit for orchestration, Cartesia for text-to-speech, OpenAI for language understanding, and Deepgram for speech recognition. Suitable as a starting template for building custom voice AI applications.
Kubernetes SRE Voice Agent with MCP ToolsA conversational voice assistant for Site Reliability Engineering and Kubernetes operations. Uses Model Context Protocol tools to list, describe, scale, and manage Kubernetes resources through natural language. Integrates with external MCP servers for flexible DevOps workflows and supports A2A agent skills for multi-agent collaboration.
Dental Office Appointment Scheduling AgentAn inbound telephony voice agent that handles appointment scheduling for a dental office. Callers can check availability, book appointments, look up existing appointments, and cancel bookings through natural voice conversation. Built as a reference implementation with webhook security and Twilio request signature validation.
Inbound Phone Order Status AgentA production-ready inbound phone agent that answers calls, transcribes the caller in real time, looks up order status, and offers human handoff. Built with AssemblyAI Universal-3 Pro Streaming for speech recognition, GPT-4o for conversation and function calling, and ElevenLabs for voice synthesis. Maintains 8kHz mulaw audio end-to-end with no resampling, achieving 600-1100ms turn latency.
Multi-Agent In-App Voice Assistant with Web Search, Knowledge Base, and Account ActionsA modular voice assistant built with OpenAI Agents SDK that routes user queries to specialized agents for web search, product knowledge retrieval, or account management. Demonstrates orchestrating multiple agents with the Responses API, FileSearchTool, WebSearchTool, and custom function calling, plus voice optimization with TTS model instructions.
Conversational Phone Agent with Natural InterruptionsA voice agent that handles inbound and outbound phone calls with natural conversation flow, supporting user interruptions and multi-turn dialogue. Uses streaming speech recognition and text-to-speech for low-latency responses over standard telephone lines.
Multi-Agent Voice Pipeline with Transcription and SynthesisA three-agent crew that processes spoken audio end-to-end: one agent transcribes speech, a research analyst extracts key insights, and a speaker agent delivers the analysis as spoken audio. Demonstrates sequential multi-agent coordination with voice input and output.
Multi Agent Voice Framework for Customer Service and Chat SupervisionA demonstration framework for building advanced voice AI agents using OpenAI's Realtime API and Agents SDK. Features two core patterns: chat-supervisor (where a voice agent delegates complex tasks to a text-based supervisor model) and sequential handoffs (where specialized agents transfer users between them). Includes examples for customer service, authentication, returns processing, and sales with state machine prompting and output guardrails.
Dental Clinic Appointment Booking AgentAn AI-powered appointment booking agent that streamlines scheduling for dental clinics and healthcare businesses. The agent integrates with Google Calendar and Gmail to check available time slots, confirm bookings, send draft confirmation emails, and make outbound confirmation calls. Users can book appointments, receive queue updates, and get confirmations via email or phone call.
Content Filtering Voice Assistant with GuardrailsA voice AI assistant that answers questions about Cartesia, voice AI technology, and the competitive landscape while enforcing conversation guardrails. The agent preprocesses user inputs to detect and block toxic content, prompt injection attempts, and off-topic conversations, with escalation policies for repeated violations.
Customer Support Agent with Ticket Status LookupAn empathic voice agent that handles customer support calls, authenticates callers, clarifies issues, and provides ticket status updates via tool calls. The agent demonstrates dynamic session variable usage and mid-conversation voice switching capabilities.
Healthcare Clinic Voice ReceptionistA voice-first AI receptionist for medical clinics that books appointments, answers FAQs, recognizes returning callers, and escalates to staff when needed. Built for low-latency conversational feel using real-time streaming over WebRTC.
LangChain Agent Voice Demo with Vocode CoreA demonstration application that integrates LangChain agents with Vocode Core to enable conversational voice interactions powered by LangChain tooling. This template showcases how to build voice agents that leverage LangChain's agent framework for complex reasoning and tool usage in voice conversations.
AI Sales Agent for B2B Product OutreachAn intelligent voice agent that automates B2B sales outreach by calling potential clients to pitch products. The agent evaluates client interest and routes positive responses to human sales agents, schedules follow-ups for neutral reactions, and drops uninterested leads to optimize conversion efficiency.
General Assistant Voice Chatbot with Audio StreamingA voice AI assistant that receives calls through Plivo, transcribes caller speech using Deepgram, generates contextual responses via OpenAI, and converts replies back to natural speech with ElevenLabs. Designed to handle general queries across various fields with polite, helpful conversation.
Real-Time Web Form Filling Voice AgentA voice agent that conducts phone questionnaires while automatically filling out web forms in real-time using browser automation. The agent collects answers through natural conversation and asynchronously fills form fields in the background, maintaining smooth conversation flow without blocking.
Technical Interview Practice Agent with Real-Time FeedbackAn AI interviewer that conducts technical job interviews with real-time parallel analysis by three specialized evaluation agents. The system provides structured feedback on technical expertise, communication skills, and logical reasoning, helping candidates practice and improve their interview performance through voice-based interactions.
Spanish Dental Clinic Receptionist AgentA Spanish-first AI receptionist that handles appointment scheduling, service inquiries, and patient onboarding for dental clinics and healthcare SMBs in Latin America. Provides 24/7 phone coverage with low-latency Mexican Spanish voice, integrates with clinic knowledge bases, and offers appointment booking with WhatsApp confirmations.
Conversational AI Agent with Streaming STT and TTSA technical demonstration of a conversational AI agent that combines streaming speech-to-text and text-to-speech capabilities. The agent engages users in natural language interactions using Deepgram's Agent API, showcasing real-time voice conversation with low latency and natural responses. Built with Next.js and React, it demonstrates how to build virtual assistants, educational tutors, and customer service applications.
Multi Purpose Voice Agent ShowcaseA collection of interactive voice agent templates demonstrating customer support, language tutoring, appointment scheduling, interview practice, phone triage, and lead capture use cases. Built on AssemblyAI's Voice Agent API with real-time tool calling and turn detection.
Phone Based Voice Agent with Web SearchA production-ready voice agent that answers phone calls through Twilio, engages in natural interruptible conversations, and performs real-time web searches using tool calling. The agent bridges Twilio Media Streams to a voice AI backend using G.711 mu-law audio passthrough without transcoding.
Web Research Assistant with Real-Time SearchA voice agent that performs web searches using Exa API and synthesizes search results into natural conversational responses. The agent can answer questions by searching the web in real-time and providing comprehensive summaries of the findings.
Festival Group Planning AssistantA voice-based AI assistant that helps friend groups coordinate festival trips through phone conversations. Users call in to form groups, browse festival catalogs, track members, and manage plans using natural dialogue. The agent handles inbound calls, identifies callers by phone number, and uses tools to save groups, members, festivals, and artists to a Postgres database.
Streaming Voice Agent with Gemini Flash and Silero Barge-InA native orchestration voice agent that uses Google Gemini 2.0 Flash for conversation, Deepgram Nova-2 for real-time speech recognition, Cartesia Sonic-2 for text-to-speech synthesis, and Silero VAD for client-side voice activity detection and barge-in support. Handles both inbound and outbound calls over Plivo telephony with asyncio-based concurrent audio pipelines.
Hotel Front Desk ReceptionistA voice agent that handles hotel front desk interactions including booking inquiries, reservations, and general guest services. Designed as a testing platform for real-time speech recognition and turn-detection configurations over telephony, with detailed session logging for analysis.
SMS One-Time Password Verification for Identity ConfirmationA voice agent that verifies caller identity through SMS-based one-time password authentication. The agent collects caller information, generates a six-digit verification code, sends it via SMS, and validates the code through voice interaction. After two failed attempts, the call is terminated for security.
Multimodal Voice and Vision Assistant for iOSA voice AI assistant with realtime audio and video input capabilities. Built for iOS, it supports front and back camera switching, natural voice conversations, live screen sharing, and background operation. The assistant can observe and interact seamlessly while users work on other tasks, making it suitable for hands-free assistance scenarios.
Medical Office Receptionist for Appointment Booking and TriageA real-time voice AI receptionist for medical practices that handles inbound patient calls, books appointments, processes prescription refill requests, takes messages for callbacks, and routes urgent queries to human staff. Uses LangGraph for intelligent conversation orchestration and multi-turn appointment booking workflows.
Interactive Choose Your Own Adventure StorytellingA voice-driven interactive storytelling experience that guides users through a choose-your-own-adventure narrative. The agent periodically prompts users for input to shape the story direction, generates contextual images to illustrate each story page, and creates an immersive audio-visual narrative experience.
Barbershop Appointment Scheduling ReceptionistA voice AI receptionist for barbershops that handles appointment booking, cancellations, and inquiries over the phone. Customers call a real phone number and speak naturally to manage their appointments without needing an app or website. Uses OpenAI function calling for real-time availability checks and atomic multi-slot booking to prevent double-booking.
OpenClaw Phone Assistant with Semantic Turn DetectionA phone-based voice interface for OpenClaw that uses Deepgram's semantic turn detection to understand when callers are finished speaking, not just when they stop making noise. Supports inbound calls via Twilio or Telnyx with low-latency responses and natural barge-in capabilities.
Phone Call Handling Voice AgentA voice AI agent that handles real-time phone calls with speech-to-text, AI responses, and text-to-speech streaming over WebSocket for low latency communication.
Multi Intent Call Router with RAG InstructionsA voice assistant that identifies caller intent through conversation, then retrieves tailored instructions via RAG to handle requests like service inquiries, person transfers, and appointment scheduling. The assistant routes calls based on detected intent and executes dynamic workflows pulled from an external knowledge base.
Vonage Voice API WebSocket Connector for Multiple AI EnginesA middleware application that connects Vonage Voice API calls (PSTN, SIP, WebRTC) to various AI engines via WebSockets. Supports inbound and outbound calling scenarios and integrates with Deepgram Voice Agent, OpenAI Realtime API, ElevenLabs Agent, Hume EVI, and custom AI pipelines through connector servers.
Desktop Robot Assistant with Voice-Controlled ManipulationA voice-controlled desktop robot assistant system that performs manipulation tasks like desk cleaning and organization through natural language commands. The system coordinates multiple operators including PID-based motion control, trained ACT policies for pick-and-place operations, and MolmoAct2 VLA for generalized manipulation. The architecture demonstrates distributed robotics with the voice agent, policies, slider control, and VLA running on separate machines connected via LiveKit Portal.
Smart City Voice AI Demo for Harbour City OperationsA voice AI agent for a fictional smart city (Harbour City) featuring hot-word activation ('Hey Eve') and 16 mock functions across 4 interactive scenarios: Command & Control (power grid), Frictionless Resident (pod/coffee/HVAC), Smart Work (revenue/projections/decks), and Proactive Guardian (flood gates/alerts). Includes dynamic dashboard updates driven by LLM function calls, conversation persistence, audio interruption handling, and a futuristic minimalist UI.
Weather Information Assistant with Function CallingA conversational voice agent built with Pipecat that provides weather information through function calling. The agent demonstrates multilingual capabilities with support for English and Arabic, and can be deployed to web or phone via Twilio integration.
General Purpose Conversational Voice Agent with NVIDIA NIMA blueprint demonstrating a conversational AI voice agent built with Pipecat framework using NVIDIA NIM infrastructure. The agent uses Meta's Llama 3.3 70B Instruct model for natural language understanding and NVIDIA Riva for speech-to-text and text-to-speech. This example showcases vendor-neutral voice agent architecture with customizable system prompts for various conversational applications.
Multi-Agent Voice AI Workflow with PythonA template demonstrating coordinated multi-agent voice workflows for building complex voice AI applications. Multiple agents work together to handle different aspects of conversation flow, with real-time communication capabilities for frontend integration.
Real-Time Speech Transcription FrontendA Next.js-based speech transcription frontend that integrates with LiveKit for real-time audio transcription. The application requires a companion transcription agent to process audio streams and display transcribed text. Built with TypeScript and React, it demonstrates a minimal frontend implementation for LiveKit's transcription capabilities, typically paired with backend agents using Groq for speech-to-text processing.
Telephony Integration Connector for Conversational AIA WebSocket connector that bridges Vonage Voice API and Video API calls to ElevenLabs Conversational AI agents. Supports inbound and outbound PSTN calls, SIP trunks, Audio WebRTC clients, and Video WebRTC clients across multiple platforms. Enables voice calls from cell phones, landlines, and web applications to interact with speech-to-speech AI agents.
Healthcare Prescription Savings Outreach AgentA voice agent that conducts outbound calls to patients about prescription savings programs, comparing current medications with recommended alternatives. The agent greets patients by name, discusses their medication records, and provides personalized information about cost-saving opportunities through natural conversation.
Pizza Ordering Voice AgentA hands-on workshop template demonstrating voice-based pizza ordering. Customers speak naturally to browse the menu, add items to their cart, and place orders through a real-time conversational AI agent that handles speech recognition, natural language understanding, and voice responses.
Clinical Trial Recruitment Voice AgentVoice agent template for healthcare organizations to automate clinical trial recruitment calls. Handles patient screening, eligibility verification, and appointment scheduling for clinical research studies using conversational AI integrated with contact center infrastructure.
Medical Assistant for Clinical Note TakingA voice agent that assists healthcare professionals with clinical documentation by conducting patient interviews and generating structured medical notes. The agent collects patient information, symptoms, and medical history through natural conversation, streamlining the documentation workflow for medical practices.
Built a stack worth forking?

Open a PR or drop it in the form.

Both land in the same queue.

Submit a template