Build a voice AI agent that answers calls, qualifies leads, books appointments, and transfers to a human when needed, all from a drag-and-drop workflow builder in your browser. Dograh ships as a Docker Compose stack (API, web UI, Postgres, Redis, MinIO) that you self-host on any Linux server with automatic HTTPS provisioning via Let's Encrypt. The visual workflow builder lets you design multi-turn conversation flows by connecting nodes for greetings, intent classification, tool calls, and handoffs; describe your use case in plain English and the platform generates the LLM prompt and node graph for you. Connect your own speech-to-text, LLM, and text-to-speech providers (OpenAI, Anthropic, Gemini, ElevenLabs, Deepgram, local Whisper, Kokoro, or any OpenAI-compatible endpoint) or use the built-in Speech-to-Speech mode with Gemini Flash Live and GPT-Realtime-2 for sub-200ms latency. Telephony plugs in through Twilio, Vonage, Vobiz, or Cloudonix for inbound and outbound calling, with live agent transfer when the conversation needs a human. Webhook tool calls connect to Salesforce, HubSpot, Google Calendar, Cal.com, or any REST API without writing orchestration code. The ClonedVoice feature mixes real human voice recordings for high-frequency phrases with neural TTS fallback for dynamic content, cutting costs while improving caller trust. A built-in MCP server lets AI coding agents like Claude Code or Cursor design, test, and edit workflows through natural language. Deploy on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. BSD 2-Clause licensed.

VoicEra lets you run your own voice AI phone platform, where callers talk to agents you configure and every recording and transcript stays on infrastructure you control. Build telephony agents that answer inbound calls or run outbound campaigns, choose the speech recognition, language model, and speech synthesis behind each one, and swap providers without rebuilding the platform. Connect phone numbers through telephony carriers, route live audio through the real time runtime, and let workers execute campaign calls in the background while you watch progress from the operator dashboard. Review call logs with recordings and transcripts after each conversation, including provider recordings when carriers supply them. Serve callers in Indian and low resource languages by combining Bhashini, AI4Bharat, and other Indic models, switch languages mid call, or run speech and language models locally through the optional model server gateway. Add new AI or telephony providers behind stable registry interfaces when a better model or carrier appears, authenticate operators, and keep media in your own object storage and database. Test agents in the browser before any phone number is involved, then scale the same configuration to real calls. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

Your front desk phone rings at midnight and nobody sane is awake; QuickVoice answers it with an AI agent you configured, on servers you own, with call recordings you control. Build agents in the web console: write the prompt, pick speech-to-text, language model, and voice, set the first message, then link a real phone number from Twilio or Telnyx through LiveKit SIP trunks. Inbound callers get a receptionist that answers questions from your uploaded knowledge base, PDFs and web pages chunked and embedded for live retrieval, while outbound mode fires single quick calls or batch campaigns for reminders and follow-ups. Agents can invoke allowlisted MCP tools mid-call, so checking an order status or booking a slot happens inside the conversation instead of after it. Every call lands in the log with transcript, recording, and metadata, searchable from the analytics dashboard, and privacy controls redact personal data by default, can suppress recordings entirely, and sweep old transcripts on a retention schedule. Multi-language voices, per-agent runtime overrides for campaigns, organization accounts with API keys and audit logs, and Stripe billing hooks round out a platform built for teams who would rather inspect their voice stack than rent a black box. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Once a voice agent is imported or built, Lampline connects it to a phone line, sends an AI caller to grade real calls, and keeps it all on your own server. Start by importing a Dialogflow CX or CX Agent Studio export along with a report of anything to check, or build fresh in a drag-and-drop builder that mixes LLM steps with scripted pages for exact lines and form fields. Next, pick one of 20 model providers, including Claude, OpenAI, Gemini, Bedrock, Groq, and DeepSeek, or run Ollama with local speech and no API keys. Test by chat or microphone while each step lights up, and let agents call HTTP and MCP tools and save records in collections of their own. Then connect callers through Twilio, Telnyx, or any SIP trunk, PBX, or session border controller via jambonz, with transfers to a person that carry the call's details as SIP headers. Finally, evals phone the agent over a real line, where an AI Test Caller brings background noise, accents, and interruptions, grades each transcript check by check, and reports typical and p95 response times as callers hear them. Each agent stays a folder of YAML and Markdown that you can review in git and lint or test with the vk CLI. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

AI Native Call Center is a self-hosted call center where a voice model answers the phone first and people step in only when the conversation actually needs one. Calls land on FreeSWITCH and connect straight to a speech-to-speech provider, and a flow engine steers each call through phases that carry instructions and the tools the model may use, with transitions firing on tool results. When a person is required, the call transfers into a real queue and the agent's browser screen has already popped with the caller's details and the bot-phase transcript ready to read. Agents handle presence, call control, and callbacks from the web interface, and a companion browser extension holds their SIP registration and audio. Supervisors watch a live wallboard with the queue view and the agent roster. Persona, rules, and voice are published and versioned together, and flows are plain documents you can author and validate before loading. Every conversation, bot-answered, handed over, and finished by an agent, lands in a single call record holding one transcript and one recording stored on a filesystem or an S3-compatible bucket. The interface and the bot work in English and Chinese, with provider choices for different regions including an option to run your own realtime gateway. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

"Run the migration and call me if anything fails" is an instruction your agent can finally obey, because Agentring is the self-hosted bridge that lets AI agents ring your phone and talk it through with you. When an agent needs a decision, hits a wall, or finishes a long job, your phone rings even locked and in Doze; a realtime voice AI explains why it is calling, answers your questions, and hands the transcript back so the agent carries on with your decision. You can also call your agents back from the Android app and ask what CI said while driving; the voice AI can consult your other agents mid-call, and a slow answer arrives when ready, or as a message if you have hung up. A missed call turns into a message you can answer from the notification. Anything that speaks MCP can reach you, including Claude Code, Codex, opencode, OpenClaw, and Hermes, and scripts or n8n reach you through the REST API and CLI. Pick your voice: Gemini Live by default, OpenAI Realtime, Grok Voice, Phonic, or your own local speech server with no key at all. The relay and LiveKit run in one Docker Compose behind Caddy, the daemon sits beside your agents and connects outbound only, and FCM push wakes the locked phone. No phone numbers, no Twilio, no per-minute fees. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

With over 20,000 GitHub stars and adoption by companies building everything from telehealth platforms to AI voice agents, LiveKit is the most widely deployed open-source real-time communication server available. The Go-based Selective Forwarding Unit handles hundreds of concurrent participants per node with adaptive bitrate streaming, simulcast layers, SVC codec support for VP9 and AV1, and end-to-end encryption. Client SDKs span JavaScript, Swift, Kotlin, Flutter, React Native, Rust, Python, Unity, and ESP32 embedded devices, while server-side APIs cover Node.js, Go, Ruby, Java, Python, Rust, PHP, and .NET. The Agents framework enables building AI-powered voice and video applications — real-time speech-to-text, LLM-driven conversations, and computer vision pipelines — running as server-side participants in any room. Egress records sessions to S3-compatible storage or streams to RTMP endpoints, while Ingress pulls external feeds from OBS via RTMP, WHIP, or SRT into LiveKit rooms. The SIP bridge connects traditional telephony to WebRTC rooms for hybrid conferencing. JWT-based authentication, webhook notifications, room-level moderation APIs, and selective subscription give operators granular control. Deploy as a single binary for development, Docker Compose for production single-node, or Kubernetes with the official Helm chart for distributed multi-region clusters using Redis for state coordination. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

A SIP phone system lives or dies on the unglamorous middle. Something has to route every call, know who is registered, wake phones that are asleep, and translate between networks that disagree. Flexisip is that middle, built as a modular server suite where you deploy only the pieces your service needs. The proxy routes calls and messages, relays media with ICE, STUN, and TURN support, and authenticates users by digest, TLS certificates, or OpenID Connect. Its push gateway speaks RFC 8599 to Apple and Google, so incoming calls ring phones whose app is closed, and it can lend that gift to an existing Asterisk or FreeSWITCH platform that lacks push of its own. The presence server tracks who is reachable and shares contact lists, the back-to-back user agent bridges SIP networks to PSTN gateways and trunks with codec transcoding and caller identity translation, and a registration event server notifies peer domains when users register. Instances cluster with load balancing for services that outgrow one box, the same suite shrinks onto a Raspberry Pi class intercom, and it has quietly powered the public linphone.org SIP service for over a decade. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

Routr is a programmable SIP server that proxies, registers, and routes calls for carriers and communication platforms, replacing racks of inherited PBX plumbing with one cloud-ready process. Phones and trunks connect over UDP, TCP, TLS, WebSocket, or secure WebSocket, register against the built-in registrar, and find each other through the location service backed by memory, Redis, or Postgres. Routing is configurable per domain with intra-domain, ingress, egress, and peer-egress strategies, and multi-tenant domains carry their own access control lists. Load balancing with session affinity spreads calls across Asterisk and FreeSWITCH media servers, and RTPEngine middleware anchors media and adds SDES-SRTP toward TLS trunks. Web phones authenticate with JWT endpoint credentials, and every call message can be recorded and replayed for debugging. Operators manage the whole system through a gRPC API, the Node.js SDK, or the rctl command-line tool, and custom Processors and Middleware written in JavaScript reshape SIP messages as they pass. OpenTelemetry traces, metrics, and logs expose the server's behaviour in production, and the same deployment runs from a single Docker container to a Kubernetes cluster through the published Helm charts. There is no single point of failure in the design, so a registrar outage never takes the dial tone with it. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

One Janus installation can host a video meeting in one session, stream a camera feed in another, and bridge a browser call into a telephone network in a third, because Janus is a general-purpose WebRTC server whose work is done by interchangeable plugins. The VideoRoom plugin publishes each participant's streams to everyone else in the room with simulcast and viewport selection, so a class or team call adapts quality per viewer instead of forcing one bitrate on all. Streaming mounts live or prerecorded sources, including RTSP cameras and RTP feeds, and hands them to any number of WebRTC viewers, while AudioBridge mixes voices into conference rooms with recording and signed-token access. SIP and NoSIP plugins register with existing VoIP infrastructure and place or receive calls, translating between WebRTC media and telephone audio so a web page can ring a desk phone. Record&Play captures publisher streams to files you can replay through the same server, TextRoom adds data-channel chat rooms, and Lua or JavaScript plugins let you script custom media logic without recompiling the core. Applications talk to Janus over HTTP or WebSocket APIs, with RabbitMQ, MQTT, and NATS transports for bus-driven deployments, and event handlers report session activity to your monitoring stack. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. GPL-3.0 licensed.

Viewers arrive on browsers, phones, and desktop players, and SRS meets each of them with the right protocol from a single published stream. A broadcaster pushing RTMP can reach browser viewers through WebRTC with sub-second latency, phone apps through HLS, and desktop players through HTTP-FLV, all from the same live source without running parallel encoders. WHIP endpoints accept WebRTC ingest from browser studios and tools like OBS, while WHEP serves WebRTC playback, so an entire publish-to-viewer path can stay on modern web protocols. Operators shape each channel with virtual hosts, authenticate publishers and players through HTTP hooks that consult your own backend, and record live streams to disk as DVR archives for replay. Forwarding republishes a stream to YouTube, Facebook, or another SRS instance, and origin clustering lets edge servers pull from a central origin so one ingest feeds viewers in several regions. The built-in HTTP API reports streams, clients, and server health for monitoring, and GB28181 support ingests surveillance camera networks alongside creator broadcasts. Configuration lives in a single reloadable file, so changing a vhost or enabling HLS rarely means restarting the listeners your audience is attached to. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A visitor clicks your link and a face is already there, listening, answering within a fraction of a second, and stopping the moment they interrupt, because Mynah runs live digital humans in the browser instead of playing back rendered video. Underneath, cored takes WebRTC offers, runs the conversation through your chosen language model, speech recognition, and text to speech, and drives a lip synced avatar engine such as MuseTalk, FlashHead, or Wav2Lip, with a semantic end of turn model deciding when a person has finished speaking. The admin console is where you shape the experience: bake a new avatar from a talking video with explicit consent, clone or audition voices, swap avatars per channel without cold starts, and tune green screen keying and gestures live in the playground. Knowledge bases take your documents through ingestion and embedding so answers ground in your material, with retrieval tests before anything ships. Publishing freezes a model, voice, and knowledge snapshot into a channel: a shareable link with token, domain, or CIDR access control, its own branding, and a concurrency cap drawn from an engine pool that computes how many workers your VRAM can hold. Session monitoring shows who is connected and lets you kick a session, health checks watch every dependency, and light and dark themes with Chinese and English interfaces cover both console and visitor pages. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

With 26,000 GitHub stars and consistent victories over ElevenLabs in blind evaluations, Chatterbox delivers state-of-the-art text-to-speech with zero-shot voice cloning requiring only 5 seconds of reference audio. The model family spans three architectures: Chatterbox Multilingual V3 (500M parameters, 23+ languages including Arabic, Chinese, Japanese, Korean, Hindi, French, German, Spanish, and Portuguese), Chatterbox-Turbo (350M parameters optimized for voice agents with a single-step distilled decoder achieving ~200ms time-to-first-speech), and Chatterbox-Nano (110M parameters running 3x faster than realtime on 8 CPU cores for edge deployment). Unique among open-source TTS systems, Chatterbox introduces emotion exaggeration control — adjusting intensity from monotone to dramatically expressive via a single parameter — and native paralinguistic tagging where tokens like [laugh], [cough], [chuckle], and [gasp] inject natural vocal reactions inline without post-processing. The alignment-informed inference pipeline eliminates hallucinations and repetition artifacts common in autoregressive TTS. Built-in PerTh neural watermarking embeds imperceptible forensic identifiers in generated audio for provenance tracking. Trained on 500,000 hours of cleaned speech data across all supported languages. Voice conversion scripts enable transforming existing audio into any cloned voice. Deploy via pip install with PyTorch, serve through Gradio interfaces or custom FastAPI endpoints, and expose via HTTP streaming or WebSocket for sub-200ms conversational applications. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Kokoro-FastAPI turns text into natural-sounding speech across eight languages by serving the 82-million-parameter Kokoro-82M model through an OpenAI-compatible REST API, so any existing OpenAI SDK client can generate audio by just changing the base URL. With over 5,300 GitHub stars since December 2024, the fully Dockerized FastAPI server covers American English, British English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese with language-specific phoneme processing. Inline voice mixing blends multiple profiles using weighted ratios like af_bella(2)+af_heart(1), automatically normalizing weights and caching combined voicepacks as PyTorch tensor files for reuse. Audio streams in real time over HTTP with configurable chunk sizes, or generates complete files in MP3, WAV, OPUS, FLAC, AAC, or PCM formats with speed control from 0.25x to 4.0x. Per-word timestamped captions with speaker-tagged voice labels enable subtitle generation for podcasts, audiobooks, and accessibility workflows. Pre-built Docker images support NVIDIA GPU acceleration via CUDA, experimental AMD GPU inference via ROCm, and CPU-only deployment on linux/amd64 and linux/arm64 architectures, with Apple Silicon MPS support available through direct UV execution. The integrated web interface at port 8880 provides browser-based speech generation, while the Swagger UI at /docs exposes the full API reference. Debug endpoints report system statistics for monitoring inference load. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

OpenVoiceUI is the voice-first front end for a self-hosted AI agent that lives entirely on your own hardware; you talk, it answers out loud, and it builds live pages on screen while the conversation runs. Hold a hands-free conversation with wake word, push-to-talk, and the ability to interrupt, or switch to text when the room is quiet. Speech recognition runs in the browser for free or through Deepgram, Groq Whisper, or your own Whisper server, while nine speech providers from local Supertonic to ElevenLabs give the agent its voice, cloned voices included. As it talks, the agent opens live canvas pages, dashboards, galleries, reports, and tools, and files them on an OS-style desktop you can reopen from the start menu. Ask for music and it generates songs with a built-in player and playlists; ask for images and it creates those too, alongside an audio clip maker and a soundboard. Profiles swap the agent's persona, voice, and model provider, animated faces react while it speaks, and sub-agents and workspace files stay visible in the admin dashboard. The agent itself runs in the OpenClaw gateway with your choice of model provider, so your keys, conversations, and files never leave your server. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Call-Me puts a click-to-call video button on your website so a visitor can start an encrypted one-to-one video call with your team right in the browser, with no downloads, no accounts, and no phone numbers. A shared link carries everything: send a customer to a named room such as Support or Reception, or link straight to one person so the call rings them directly, which suits support desks, telehealth check-ins, tutoring, and sales consultations. Everyone in a room sees who else is present and available, and one click on a name starts the call. During the call you can chat in real time, share your screen, send files, switch between cameras, microphones, and speakers, hide your video, or mute yourself. Web push notifications flag an incoming call even when your tab sits in the background, so a staffed room never silently misses a visitor. An optional host password keeps the operator side of the room private. A REST API reports connected users, rooms, availability, and active calls, and can start a call for you, while webhooks post join, leave, and call start and end events to your other systems. The interface speaks multiple languages and adapts to phones and desktops alike. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.