Voice Agents logopeterindia.net
Knowledge Hub

Voice Agents

Voice agents in one place: LiveKit and Krisp resources, open-source frameworks, platforms and realtime APIs, speech models, audio quality, telephony and testing, with related pages on this site.

137 topics•9 categories•Updated November 20, 2026

Start Here: LiveKit & Krisp

30 entries

Resources for the two platforms behind this page: LiveKit for building agents and Krisp for voice quality.

01LiveKitOpen-source framework and developer platform for building, testing, deploying, scaling and observing voice, video and physical AI agents. 02LiveKit Agents documentationDocumentation for LiveKit's realtime framework for voice, video and physical AI agents. 03LiveKit Voice AI quickstartGuide to building and deploying a simple voice assistant in under ten minutes. 04LiveKit: Turns overviewGuide to managing conversation turns, including turn detection and interruptions, in voice AI. 05LiveKit TelephonyHow LiveKit connects traditional phone networks to its realtime platform so agents can take and make calls. 06LiveKit: Debugging and testing agentsUsing the Agent Console, the CLI debugger and unit tests to build and verify an agent. 07LiveKit Agents (GitHub)The open-source Python framework for building realtime voice AI agents. 08LiveKit Agents for Node.jsThe Node.js version of the LiveKit Agents framework for realtime multimodal agents. 09LiveKit agent starter (Python)A complete voice AI starter project for LiveKit Agents in Python. 10LiveKit serverThe open-source realtime stack for connecting people and AI agents over WebRTC. 11LiveKit blogNews, tutorials and customer stories from the LiveKit team. 12KrispVoice AI company known for noise cancellation, with products for meetings and call centers. 13Krisp Developers: Real-Time AI Voice SDKKrisp's SDK for voice AI agents and apps that removes background noise, isolates voices and converts accents. 14Krisp blogKrisp's articles on voice AI, noise cancellation and call quality. 15Krisp Developer DocsDocumentation for Krisp's real-time voice AI SDKs for agents and calls, and its cloud API for voice isolation and translation. 16LiveKit: Models overviewGuide to choosing the speech, language and other models for a LiveKit voice agent. 17LiveKit: Agent speech and audioSpeech and audio capabilities available to LiveKit agents. 18LiveKit: Tool definition and useHow to let LiveKit agents call external tools. 19LiveKit: WorkflowsHow to model repeatable workflows through agents, handoffs and tasks. 20LiveKit: Agent deployment overviewOverview of deploying agents, including secrets, builds, logs and monitoring. 21LiveKit: Agent frontendsBuilding custom web or mobile frontends for a LiveKit agent. 22LiveKit: Egress overviewUsing LiveKit's Egress service to record or livestream a room. 23LiveKit SIPOpen-source SIP to WebRTC bridge for LiveKit. 24LiveKit Python SDKsLiveKit realtime and server SDKs for Python. 25LiveKit CLICommand-line interface to LiveKit. 26LiveKit React componentsOfficial open-source React components and examples for building with LiveKit. 27LiveKit Swift SDKClient SDK for live audio and video on Apple platforms. 28LiveKit Android SDKClient SDK for building LiveKit experiences on Android. 29LiveKit Flutter SDKFlutter client SDK for LiveKit. 30LiveKit pricingLiveKit's plans, designed to scale with your projects.

Open-Source Voice Agent Frameworks

19 entries

Frameworks and building blocks for assembling a voice agent yourself.

31Pipecat documentationDocumentation for Pipecat, the open-source framework for voice agents and multimodal realtime apps. 32Pipecat (GitHub)Open-source framework for voice agents, multimodal apps and realtime AI, maintained by Daily and the community. 33Pipecat Smart TurnOpen model project for detecting when a speaker has finished their turn. 34Pipecat FlowsOpen-source framework for structured dialogues in Pipecat voice agents. 35Pipecat examplesExample applications that show patterns for building voice AI with Pipecat. 36DailyRealtime voice, video and AI platform from the team behind Pipecat. 37VocodeModular open-source library for building voice-based LLM agents. 38TEN FrameworkOpen-source framework for conversational voice AI agents. 39jambonzSelf-hosted voice platform for building custom voice AI with any AI service and your own telephony. 40DograhOpen-source, self-hosted voice AI platform positioned as an alternative to hosted voice agent platforms. 41Pipecat CloudDaily's hosted platform for deploying Pipecat voice agents at scale. 42Pipecat supported servicesList of speech, language and other services that Pipecat integrates with. 43Pipecat client SDK for the webReal-time voice inference web SDK for Pipecat. 44Pipecat prebuilt clientReady-to-use client for development, debugging and prototyping with Pipecat. 45Daily AI toolkitDaily's documentation for building AI voice and video features. 46jambonz feature serverCore telephony feature server of the jambonz platform. 47OpenAI Realtime AgentsOpenAI demo of more advanced agent patterns built on the Realtime API. 48OpenAI Agents SDK: voice quickstartQuickstart for building voice agents with the OpenAI Agents SDK. 49OpenAI: Voice agents guideOpenAI's guide to choosing a voice architecture and connecting conversations to agent workflows.

Voice Agent Platforms & Realtime APIs

17 entries

Hosted platforms and model-provider APIs for voice agents.

50VapiDeveloper platform for building, testing and deploying voice AI agents that make and receive phone calls. 51Retell AIPlatform for building, testing, deploying and monitoring voice and chat agents for contact centers. 52BlandEnterprise voice AI platform for phone agents with self-hosted models. 53ElevenLabs AgentsElevenLabs' platform for building, testing and deploying voice and chat agents. 54SynthflowEnterprise AI voice agents for phone calls. 55UltravoxReal-time, speech-native voice AI infrastructure layer for voice agents. 56Deepgram Voice Agent APIDeepgram's API for real-time voice agents that combine speech-to-text, an LLM and text-to-speech over one WebSocket. 57OpenAI Realtime APIOpenAI's API for low-latency, speech-to-speech and voice agent applications. 58Gemini Live APIGoogle's API for low-latency, real-time voice and video interactions with Gemini. 59Azure Voice Live APIMicrosoft's API for real-time voice agents in Foundry Tools. 60Amazon Nova SonicAmazon's speech-to-speech model for spoken conversations. 61SarvamIndian AI platform with speech-to-text, text-to-speech, translation and conversational agents across 22 Indian languages. 62AgoraReal-time engagement and conversational AI platform. 63Hume AICompany focused on emotionally intelligent voice AI, with voice-native evaluation tools. 64Ultravox documentationDocumentation for Ultravox Realtime. 65ElevenLabs API documentationAPI docs for text to speech, speech to text and voice agents. 66Smallest AIVoice AI platform with text-to-speech, speech-to-text and voice agent APIs.

Speech Models: STT, TTS & Speech-to-Speech

34 entries

Models and comparisons for hearing, speaking and conversing.

67Deepgram FluxDeepgram's speech recognition model built specifically for voice agents. 68AssemblyAISpeech AI models for transcription and speech understanding. 69SpeechmaticsSpeech-to-text APIs for voice AI, covering accents, multiple speakers and multilingual audio. 70OpenAI WhisperOpen-source speech recognition model trained with large-scale weak supervision. 71faster-whisperA faster Whisper implementation using CTranslate2. 72NVIDIA NeMoNVIDIA's framework for language, multimodal and speech AI, including speech recognition and synthesis. 73CartesiaReal-time voice AI company with text-to-speech, speech-to-text and voice agents. 74RimeConversational voice models for enterprise voice agents. 75Fish AudioText-to-speech and voice cloning platform. 76KokoroSmall open-weight text-to-speech model. 77Orpheus TTSOpen text-to-speech project aimed at human-sounding speech. 78Moshi (Kyutai)Speech-text foundation model and full-duplex spoken dialogue framework. 79Sesame CSMConversational speech generation model from Sesame. 80Open ASR Leaderboard (Hugging Face)Interactive leaderboard of speech recognition models by language, dataset and word error rate. 81Artificial Analysis: Text to SpeechComparison of speech generation models by quality, speed and price. 82Artificial Analysis: Speech to TextComparison of speech-to-text providers by word error rate, speed and price. 83GladiaAudio infrastructure that transcribes and enriches conversations through a single API. 84SonioxSpeech AI API for realtime speech-to-text, text-to-speech and translation in many languages. 85Inworld TTSInworld's text-to-speech and voice cloning for realtime voice agents. 86Chatterbox (Resemble AI)Open-source text-to-speech model. 87F5-TTSOpen-source flow-matching text-to-speech model. 88PiperFast, local neural text-to-speech system. 89Coqui TTSDeep learning toolkit for text-to-speech. 90DiaText-to-speech model that generates dialogue in one pass. 91MoonshineVery low latency speech-to-text, intent recognition and text-to-speech for voice agents and interfaces. 92Kyutai Delayed Streams ModelingKyutai's streaming speech-to-text and text-to-speech models. 93LLaMA-OmniLow-latency end-to-end speech interaction model built on Llama 3.1. 94Moshi: a speech-text foundation model for real-time dialogue (arXiv)Paper describing Moshi, a full-duplex speech dialogue model. 95Robust Speech Recognition via Large-Scale Weak Supervision (arXiv)The Whisper paper. 96TTS ArenaHugging Face space where listeners compare text-to-speech models and vote. 97Google Cloud Text-to-SpeechGoogle Cloud's text-to-speech service with Gemini-powered voices. 98Amazon PollyAWS text-to-speech service. 99Amazon TranscribeAWS automatic speech recognition service. 100Azure SpeechMicrosoft's speech recognition and text-to-speech services.

Audio Quality & Voice Activity Detection

6 entries

Cleaning audio and detecting speech before it reaches the model.

Telephony & Real-Time Infrastructure

8 entries

Phone networks, SIP and WebRTC plumbing that connects agents to callers.

Testing, Evaluation & Learning

7 entries

Tools and guides for checking that a voice agent behaves.

Related Technologies on This Site

11 entries

Agent, chatbot, speech analytics and observability pages on this site.

122Autonomous AgentsGuide to autonomous agents: OpenHands, AutoGPT and Devin, agent SDKs from OpenAI and Anthropic, benchmarks such as SWE-bench, and safety frameworks. 123AI Chatbot Development PlatformsCompare 21 AI chatbot development platforms for 2026 — Botpress, Rasa, Dify, Voiceflow, Copilot Studio, Amazon Lex, Cognigy and more. 124Conversational AI Platforms for Customer ServiceDirectory of 14 conversational AI platforms for customer service in 2026: NiCE Cognigy, Kore.ai, Omilia, Yellow.ai, Sierra, Intercom, PolyAI and Rasa. 125Conversational AI Platforms for Employee ServicesConversational AI platforms for employee services for 2026: Moveworks, Aisera, Avaamo and Kore.ai, providing virtual assistants for IT and HR support. 126Speech Analytics ModulesSpeech analytics modules for 2026: 2MARES, Amazon Connect Contact Lens, Avaya Experience Platform and JustCall. 127Audio AnalyticsDirectory of audio analytics in 2026: speech recognition and transcription, speaker diarization, audio feature and sound-event libraries, cloud… 128A Technical Overview of AI Agent ObservabilityOverview of AI agent observability: monitor, trace and evaluate autonomous agents with MELT data, OpenTelemetry GenAI conventions and tools such as… 129Guardrails for an AI AgentGuardrails for an AI agent in 2026: five checkpoints (input, retrieval, tool-call, output, human approval) with Llama Guard, Presidio, NeMo, OPA and… 130Agentic AI Communication Protocols: MCP, A2A, Agent Client Protocol & MoreGuide to agentic AI communication protocols in 2026: Model Context Protocol (MCP) for tools, Agent2Agent (A2A) for agent collaboration. 131Multi-Agent Orchestration FrameworksMulti-agent orchestration frameworks for 2026 by style: LangGraph, CrewAI, Google ADK, Microsoft Agent Framework, OpenAI Agents SDK, protocols and… 132Edge AIEdge AI directory for 2026: hardware, runtimes, model optimisation, small language models, edge MLOps and benchmarks, from Jetson to LiteRT and…

Frequently Asked Questions

What is a voice agent?

A voice agent is an AI agent you talk to. It listens with speech recognition, reasons with a language model, speaks with text-to-speech, and can call tools or take actions, usually over a phone line or a web or mobile app. Some newer systems use speech-to-speech models that skip the separate text step.

What are the main parts of a voice agent?

Common components are speech-to-text, a language model, text-to-speech, voice activity detection and turn detection to know when the person has finished speaking, and a transport layer such as WebRTC or SIP telephony. LiveKit Agents and Pipecat are open-source frameworks that wire these together.

What do LiveKit and Krisp do?

LiveKit is an open-source framework and developer platform for building, testing, deploying and observing realtime voice, video and physical AI agents. Krisp provides noise cancellation and other voice AI technology, and its developer SDK is aimed at voice agents and apps. Krisp has described its voice-isolation and turn-prediction products for agents, and its performance figures are vendor-reported.

Why do turn detection and noise handling matter?

Agents that mistake background sound for speech interrupt people or lose the thread, and ones that wait too long feel slow. Turn detection decides when a speaker is done, and noise cancellation and voice activity detection improve what the model hears. LiveKit documents its turn handling, and Pipecat has an open Smart Turn model.

How do I test a voice agent?

Test with simulated conversations before launch and score real calls afterward. LiveKit offers an agent console, a CLI debugger and unit tests, and tools such as Hamming, Coval, Cekura and Roark simulate calls and evaluate production conversations.