Open Source Voice Agents

Voice.ai offers cloud‑and on‑prem AI voice agents for calls, scheduling, and queries, supporting 15+ languages. It provides text‑to‑speech, 10‑second voice cloning, real‑time voice change, noise filtering, and integrates with Salesforce, HubSpot, Zendesk, Slack. APIs and SDKs enable scalable deploym

Open Voice OS is an open-source, community-driven voice AI platform for building customizable assistants across Raspberry Pi, embedded devices, Linux desktops, and Docker. It provides plugin-based STT/TTS, configurable wake words, extensible skills, and privacy-focused self-hosting.

ElevenCreative is an AI tool that generates ultra-realistic speech, videos, music, and sound effects, offering text-to-speech, voice cloning, and a library of pre-recorded voices for creating personalized content for various applications.

DeepSeek-V3 is an advanced AI model offering leading performance in open source LLM, enhanced speed, and global language support. It sets new benchmarks for inference speed among open-source models.

A web‑based Microsoft AI TTS tool offering 330+ neural voices in 129 languages. Users can adjust rate, pitch, pauses, and style for news, scripts, or narration. Works across Chrome, Firefox, Edge, with an API for web integration.

11 ai is a voice assistant using ElevenLabs Agents that enables voice-driven task management, customer research, ticket updates, and team messaging via integrations with Perplexity, Linear, and Slack, supporting private MCP servers and fast voice cloning across 5,000+ voices.

Voiceflow enables teams to create, test, and deploy AI‑powered conversational agents across chat, voice, phone, and web without coding. Its visual editor, real‑time collaboration, and secure deployment pipelines streamline design, evaluation, and omnichannel rollout.

OpenAI.fm is an interactive text-to-speech demo that lets users explore various voice styles and emotional tones, enhancing storytelling in gaming and multimedia by enabling customizable audio outputs with dynamic pacing and expressive characteristics.

Voice AI platform that builds conversational agents in five clicks, automating support, sales, and billing calls. It integrates natively with CRMs and databases for real‑time actions, supports multi‑OS softphones, and records transcriptions for audits.

Sesame AI is an advanced AI voice model that generates natural and expressive speech. It provides human-like voices with multi-language support, real-time generation, and customizable voice parameters, ideal for content creators, developers, and businesses.

Kokoro Web is an open-source AI voice generator offering multilingual text-to-speech capabilities with customizable accents. It features user-defined input profiles, self-hosting options, and model quantization for optimized performance, catering to developers and content creators.

VoiSpark is an AI voice generator for text-to-speech and voice cloning, offering 500+ natural voices in 30+ languages. It enables custom emotions, styles, and unique vocal identities, with seamless integration for voiceovers in videos, podcasts, and apps.

Voicemaker is a cloud‑based text‑to‑speech platform offering 1,500+ AI voices in 130+ languages. It lets users adjust pitch, speed, pauses, add effects, clone voices with a minute of audio, and export to MP3, WAV, OGG, AAC, or OPUS.

Noiz Agentis a next‑gen AI voice platform for voice cloning, emotion‑aware text‑to‑speech and multilingual dubbing, tailored for podcasters, audiobook narrators, video producers and developers. It offers one‑prompt voice generation, scene‑based emotion controls (whisper, laugh, pause), pro audio ed

YesChat.ai unifies chat, music, video, and image generation in a browser platform, offering DeepSeek‑R1, GPT‑4o, and Claude 3.5 Sonnet for conversation, royalty‑free music from text, text‑to‑video, and image creation. It supports languages and customizable bots for research and marketing.

PlayAI turns text into natural‑sounding audio in 42+ languages using 800+ voices. Users adjust pitch, rate, volume, add SSML pronunciations, support multi‑speaker real‑time synthesis, voice cloning, and API integration for chatbots, streaming, IVR, e‑learning.

SpeechGen.io converts up to 2 million characters into high‑quality neural‑voice audio across 150 languages with 5,000 models. It allows voice, speed, pitch, volume control, SSML tags, background music, multi‑speaker tagging, downloadable formats, and a REST API.

Claude is an advanced AI assistant designed for a variety of tasks, including code generation, writing, productivity enhancement, and business automation. It is highly adaptable, intelligent, and customizable to meet diverse user needs.

ZeroBot lets users create role‑specific AI agents with custom voice, avatar, and behavior, supporting GPT‑5, Gemini, Claude, Llama, and Qwen. It offers actions, connectors, web search, image generation, and human‑backed verification for secure, versatile use.

Hume AI offers emotion‑intelligent text‑to‑speech, real‑time speech‑to‑speech, and expressive voice cloning across 100+ languages. Developers use TypeScript, Python, .NET, or Swift SDKs to build voice‑design, stage‑direction, and emotion‑analysis features for content creation.

Uncensored AI delivers a chat platform featuring Claude Opus, Gemini, Grok, and MiniMax M2‑Her. It supports text, audio, image, and code interactions, including image‑to‑video via Image Studio. API beta and usage stats benefit developers, writers, educators, and researchers.

Voicera is an AI tool that automatically creates life-like voice dictations of blog articles with one click, supports over 200 languages and dialects, and benefits content creators and brands.

StarVoice is an AI voice generator that lets users create celebrity‑style vocal clips and clone their own voice. It offers a licensed voice library, daily new characters, multi‑language TTS, and community support.

Omakase.ai is a voice AI chatbot that converts websites into interactive voice sales agents for real-time customer conversations. It offers setup via URL, context-aware responses, guided selling, and analytics without requiring technical expertise.

OneContact unifies voice, chat, WhatsApp, and social media into a single contact‑center interface, offering real‑time agent assistance, bot automation, sentiment analysis, quality monitoring, workforce optimization, and CRM integration for global scalability.

LOVO converts text to speech using 500+ voices in 100 languages with expressive variants. Its online editor syncs audio, adds subtitles, and supports full video editing. Features voice cloning from one minute, AI script generation, royalty‑free images, and API integration.

Steosvoic is an AI tool that provides high-quality neural voice artificial intelligence for creating unique content and generating audio with over 50 voice options and multiple language support. It offers a paid plan or free version.

GitHub Next Project: Write code without the keyboard using voice commands with GitHub Copilot.

OpenAssistantGPT is an open‑source SaaS that lets you build no‑code AI chatbots for websites. It auto‑crawls a URL, supports GPT‑4/3.5, handles file attachments, SAML/SSO, API calls, and web search, with GitHub source and Vercel SDK.

OpenCode.ai is an open-source AI coding agent that runs directly in your terminal, IDE, or desktop. It connects to 75+ LLM providers, supports offline use, and enables multi-session collaboration for code review and debugging.

Vagent is a voice‑controlled chat interface that lets users converse with custom AI agents in over 60 languages. It connects to any backend via a single authenticated webhook, stores chat history locally, and supports Markdown formatting and speech synthesis.

Uberduck generates synthetic voices, text‑to‑speech, and AI music in 70+ languages. It supports voice conversion, cloning, and singing, with developer APIs and built‑in music creation for narration, branding, and marketing.

Voice Lab AI is a text-to-speech and voice cloning tool that generates realistic, expressive voices for audiobooks, voiceovers, and narration. It offers multilingual support, tonal nuance, and robust data security features like encryption and access controls.

MiniMax is an AI platform providing text, speech, video and music models for developers and creators — supporting agentic text workflows, real-time speech synthesis and voice cloning, emotion-aware video rendering, and precise vocal/instrument music generation via APIs and SDKs.

SigmaMind AI builds production voice agents without code, delivering sub‑800 ms latency and real‑time tool orchestration. It integrates with databases, CRMs, and APIs, and supports enterprise features like SOC 2 compliance, encryption, private cloud, and SIP trunking for scalable multichannel suppor

Voisi converts text into natural‑sounding speech with 450+ voices and 100+ languages, transcribes audio, translates text and audio, clones voices from short samples, and chains transcription, translation, and synthesis into single workflows.

The AI Voice Generator is a versatile tool that creates lifelike voiceovers in 120+ languages and 800+ voices from text inputs. It supports accents, genders, and celebrity mimicry, ideal for content creators and casual users.

aiclonevoicefree.com is a free AI voice cloning tool that generates realistic podcasts by uploading short audio samples (5-30s) and converting text into cloned speech. It supports multiple formats, cross-language synthesis, and offers pitch/speed adjustments with preview and download options.

OpenHuman is an open-source personal AI framework for private, on‑premises deployments and local model execution, providing an agent framework, prompt management, local speech (Whisper/Piper), integrations, Docker/one‑click deployment, and developer tooling.

Convai enables developers to create 3D conversational characters that perceive vision, voice, and gestures, integrate with Unity, Unreal, or WebGL, and are enriched via document uploads. It offers multilingual support, realistic animation, and scalable deployment across web, mobile, VR, and AR.

LoveVoice is a text-to-speech tool that converts text into natural-sounding audio with 300+ AI voices in 70 languages. It offers customizable voice settings and outputs high-quality MP3s for videos, podcasts, and more.

ChatSonic is a GPT-4 powered conversational AI chatbot with superpowers, serving as an alternative to ChatGPT for creating content.

Dasha is an AI-as-a-service platform that enables developers to build realistic voice and text conversations for apps and products using Dashascript.

Dubbing AI is a free, real-time voice changer tailored for gamers and social media users. It enables transforming your voice to match game characters or anime personas, supporting 40 languages across popular platforms for immersive social experiences.

SoundHound AI offers a conversational platform for building, deploying, and managing AI agents that listen, reason, and act. It supports customer support, ITSM, HR, and industry modules such as automotive, finance, healthcare, retail, and voice solutions on cloud or edge.

The Speak AI tool is a language data analysis and research platform with transcription, data analysis, and sentiment analysis capabilities for various types of media.

OpenAgents is an open-source framework for building and operating scalable, interoperable AI agent networks. It provides tools to launch, connect, and orchestrate agents with live monitoring, enabling collaborative applications and workflows.

OpenCraft AI is a secure, multi‑model copilot that unifies GPT‑4, Claude, and Gemini. It preserves context across model switches, keeps uploaded files accessible, auto‑formats chats into reports or decks, and generates images with consistent voice tone for streamlined workflows.

FreeTTS delivers browser‑based AI audio utilities: multilingual text‑to‑speech, accurate speech‑to‑text transcription, vocal isolation, voice enhancement, precise cut/join, and format conversion (MP3, WAV, FLAC, OGG, M4A). All processing is local and files auto‑delete after 12 hours.

Online TTS platform converts text into audio in 100+ languages with 148+ AI voices. Users can tweak speed, pitch, pause, add background music, and download MP3, OGG, AAC, OPUS, or WAV for dubbing, audiobooks, and language learning.