AI tools for building voice agents: voice and phone agents
Platforms for agents that listen and talk: phone lines, real-time speech and voice assistants. Of the 85 tools on our building voice agents page, 63 fit this narrower job. By pricing: 25 open source, 3 source-available, 8 free or freemium, 12 paid, usage-based or enterprise, 15 pricing on the maker's site. The most-starred open repos here are LiteLLM (61,465 stars), MemPalace (59,622 stars), LocalAI (49,586 stars). Most come from the voice (35), MCP & infra (8), coding (5) categories.
LiteLLM
Open-source AI gateway and Python SDK that calls 100+ LLM providers in the OpenAI format, with cost tracking, guardrails, load balancing and logging.
Added
MemPalace
Local-first AI memory system that stores conversations verbatim with a pluggable backend and serves recall to agents without API calls.
Added
LocalAI
Self-hosted engine with an OpenAI-compatible API for running LLM, vision, voice and image models on your own hardware, including agents.
Added
XiaoZhi ESP32
Open-source voice chatbot firmware for ESP32 devices that talks through LLMs like Qwen and DeepSeek and controls hardware and services via MCP.
Added
FunASR
ModelScope's speech recognition toolkit for offline, streaming and edge ASR, with VAD, punctuation, speaker diarization and OpenAI-compatible/MCP serving.
Added
Pipecat
Open-source framework for voice and multimodal conversational agents.
Added
TEN Framework
Open-source framework for real-time multimodal voice agents, including the TEN Agent demo.
Added
Vision Agents
Stream's open framework for building real-time voice and video agents with any model.
Added
Repowise
Codebase intelligence tool that indexes code, call graph, git history and docs locally and answers questions for you and your coding agent over MCP.
Added
Superagent
SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.
Added
Dograh
Self-hostable voice agent platform with a visual call-flow builder, bring-your-own speech and LLM providers and MCP control, pitched as an open alternative to Vapi and Retell.
Added
coucou
Mac notch and phone companion that monitors your Claude Code, Codex, Cursor and Gemini CLI sessions and lets you approve permissions on the go.
Added
vocode
Open-source library for building voice-based LLM agents for phone calls and apps.
Added
Qwen Audio Agent
Real-time voice runtime from the Qwen Audio team that keeps agents talking while they think and work on tasks.
Added
ripwire
Zero-dependency CLI and MCP server that gives coding agents a ranked call graph, blast radius and tests-to-run before and after edits.
Added
ElevenLabs UI
Component library on shadcn/ui with orbs, waveforms and voice-agent components for building audio and agentic apps.
Added
Agent Vault
Infisical's open-source credential broker that proxies API calls for AI agents so they never hold secrets themselves.
Added
Gemini MCP Tool
MCP server that lets Claude and other assistants call the Gemini CLI to analyze large files and codebases with its big context window.
Added
Jarvis
Private, local-first desktop AI assistant with voice and text chat, personal memory, dictation and MCP tools.
Added
ElatoAI
Realtime voice AI for ESP32 devices and toys with 100+ speech and LLM model options.
Added
VoiceMode
Adds natural voice conversations to Claude Code and other assistants.
Added
Unbrowse
Turns websites into APIs agents can call.
Added
joinly
Connector middleware and MCP server that lets AI agents join video calls and take part in meetings in real time.
Added
TryVoice
Hands-free voice runtime for coding agents with wake word, push-to-talk and streaming replies.
Added
Cicero
Self-hosted voice interface for coding agents (Claude Code, Codex, ACP); talk from a browser or Telegram call.
Added
Stack Overflow MCP
Official remote MCP server that lets coding agents search and pull vetted Stack Overflow questions and answers, with a free daily call allowance per user.
Added
Voiceloop
Zero-dependency JS library for an interruptible in-browser voice loop (VAD, STT, LLM, TTS).
Added
11x
Digital AI workers for go-to-market teams, including an SDR agent that researches prospects and runs outbound and a phone agent that handles calls.
Added
Agentman
AI agents that run healthcare practice operations across phone calls, faxes and payer portals, with staff approving final actions.
Added
AI Emaily
AI-native email client whose assistant triages, drafts replies in your voice, schedules and sends.
Added
ASI:One
Agentic LLM and chat app from Fetch.ai built to reason, plan and call other agents on the ASI Alliance network.
Added
Bird MCP
Bird's MCP server for sending and receiving email, SMS, WhatsApp and voice messages from AI agents through one API.
Added
Bland AI
Enterprise voice AI platform for building, deploying and monitoring phone agents with self-hosted models.
Added
Bolna
Platform for building, deploying and testing voice AI agents for recruitment, sales and customer support.
Added
Cartesia Sonic
Cartesia's real-time text-to-speech API with emotion control, built for low-latency voice agents.
Added
Circleback
AI meeting notes and action items that can trigger follow-up workflows and integrations automatically after each call.
Added
ClawCall
AI that places phone calls for you, navigates menus, waits on hold and talks to the person who answers.
Added
Close
CRM with a built-in AI teammate that calls leads, qualifies prospects and books meetings.
Added
Coddo
Desktop app that puts a visual interface and voice input on top of terminal coding agents.
Added
Cognigy
NiCE Cognigy's enterprise customer service platform with generative and conversational AI agents across voice and chat.
Added
Convai
Conversational AI for virtual worlds: voice-enabled characters and agents that perceive, speak and act inside games and 3D scenes.
Added
Coval
Testing and evaluation platform for voice agents, with simulations, production evals and human QA.
Added
Deepgram
Speech-to-text, text-to-speech and voice agent APIs for building real-time voice agents.
Added
Dial
Gives an AI agent a real phone number for calls, SMS, iMessage and WhatsApp through one API.
Added
ElevenLabs Agents
Voice AI platform with conversational agents and TTS.
Added
Goodcall
AI answering service whose voice agent works as a virtual receptionist for businesses from small shops to contact centers.
Added
Hamming AI
Testing and QA platform for voice and chat agents that generates scenarios and replays real calls.
Added
Hume AI
Voice AI company focused on emotionally intelligent speech, with voice-native evaluation and human judgment tooling for voice agents.
Added
Inworld
Platform and runtime for real-time voice AI and interactive characters, including text-to-speech and agent orchestration for consumer apps.
Added
Jotform AI Agents
Build AI agents from forms and docs that answer customers via chat, voice and messaging.
Added
LiveKit Agents
Real-time voice and video infrastructure with an agents framework.
Added
NanoMuse
Open-source AI agent for your phone and computer (Show HN, Oct 7).
Added
Parloa
AI agent management platform for enterprise customer service to build, test and scale voice and chat agents.
Added
Phonely
AI phone agents that answer every call, book appointments and handle customer support for businesses.
Added
Retell AI
Builds AI phone agents for calls and support.
Added
RocketReach MCP
RocketReach's MCP server for looking up verified work emails and phone numbers from its contact database.
Added
Simple Phones
AI phone agent that answers business calls, takes messages and books appointments.
Added
Speechmatics
Speech-to-text and voice AI APIs that handle accents, multiple speakers and multilingual speech for voice agents.
Added
Synthflow
Voice AI platform for enterprise call automation that deploys low-latency phone agents for sales and support.
Added
Thoughtly
AI voice agents for inbound and outbound calls for businesses.
Added
Vapi
Platform for building and deploying phone voice agents.
Added
Voiceflow
AI agent platform for customer experience automation, for building, launching and scaling chat and voice agents.
Added
zero.xyz
Lets AI agents discover, connect to and pay per call for thousands of APIs and services without API-key setup or separate sign-ups.
Added
GitHub repos (27)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| LiteLLM ↗ | 61,465 | — | — |
| MemPalace ↗ | 59,622 | — | — |
| LocalAI ↗ | 49,586 | MIT | 2026-10-17 |
| XiaoZhi ESP32 ↗ | 31,392 | — | — |
| FunASR ↗ | 20,738 | — | — |
| Pipecat ↗ | 16,446 | BSD 2-Clause | 2026-10-17 |
| TEN Framework ↗ | 11,172 | Apache License 2.0 with additional conditions | 2026-10-18 |
| Vision Agents ↗ | 8,171 | Apache License 2.0 | 2026-09-23 |
| Repowise ↗ | 7,832 | — | — |
| Superagent ↗ | 6,766 | — | — |
| Dograh ↗ | 5,896 | BSD 2-Clause | 2026-10-18 |
| coucou ↗ | 5,468 | — | — |
| vocode ↗ | 3,804 | MIT | 2024-11-15 |
| Qwen Audio Agent ↗ | 2,936 | — | — |
| ripwire ↗ | 2,455 | — | — |
Top 15 of 27 by stars. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for building voice agents focused on voice and phone agents?
We list 63. The first three by GitHub stars and featured status are LiteLLM: Open-source AI gateway and Python SDK that calls 100+ LLM providers in the OpenAI format, with cost tracking, guardrails, load balancing and logging.; MemPalace: Local-first AI memory system that stores conversations verbatim with a pluggable backend and serves recall to agents without API calls.; LocalAI: Self-hosted engine with an OpenAI-compatible API for running LLM, vision, voice and image models on your own hardware, including agents.
Are there free or open-source options?
Yes: 25 open source, 3 source-available, 8 free or freemium, 12 paid, usage-based or enterprise, 15 pricing on the maker's site. Pricing is as each maker states it.
More from building voice agents
Tools are grouped by what each says it does. Missing one? Submit it free.