dograh
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
- 6.2k
- Python
- BSD-2-Clause
- 6 d ago
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
Open-source, self-hostable platform for building and operating AI phone agents.
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
Voice AI that runs on your own machine: speech-to-text, text-to-speech, voice cloning, diarization, and voice chat behind an OpenAI-compatible API. Desktop app, web UI, CLI, or self-hosted server.
Build realtime voice and video agents with Google's new Gemini 2.0 (API is free for now)
DialogLab is an authoring tool for configuring and running Human-AI multi-party conversations.
A programmable Voice AI platform: SIP and WebRTC call control, multi-party mixing, recording, TTS/STT, and pluggable AI agents (ElevenLabs, VAPI, Pipecat, Deepgram) — all driven through a REST API, webhooks, and a WebSocket event stream
The best performing voice isolator there is. Keeps the caller's voice and removes the other voices in the room before speech-to-text hears them. Open source, streaming, runs on CPU and in the browser. pip install voxlock
The Open Source Voice Agent Platform - Build voice agents by connecting nodes in a canvas, deploy them to handle inbound and outbound phone calls, and monitor every call, latency and cost.
Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.
Voice Prompts, GPT-4o prompts, Voice Agent Prompts, ChatGPT Prompts, HumeAI Prompts
Open Source AI Database for Voice Agent Transcripts | Call Analysis & Insights | Extraction | Labelling & Classification
Voice agents in YAML, compiled to Pipecat or LiveKit. Production code you own, deployed anywhere.
Self-hosted voice AI agents with a Vapi-compatible API. AI phone agents on Twilio, Telnyx, Plivo, Vonage or SIP, with your keys or 100% local and free (Whisper, Ollama, Kokoro). No per-minute platform fee. npx openring
Core engine behind Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations
An always-listening turn detector for voice agents, small enough (2mb / 0.5m params) to run on every 20 ms of audio.
A curated list of 150+ voice AI tools — agents, TTS, STT, cloning, telephony, frameworks. The definitive voice AI directory.
Enable calls made to your Twilio phone number to pass through to Deepgram's Voice Agent API, enabling the caller to talk to a voice agent/bot.
Backend for Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations
Frontend for Calibrate, a framework for evaluating AI agents: speech-to-text, text-to-speech, LLM evaluation, end-to-end simulations
An open-source Agent Skill that strips AI-writing tells from your prose and learns your real voice. It shapes both written and spoken output, including voice agents and voice AI. Works with Claude Code, Cursor, and Codex.
An AssemblyAI voice agent is one JSON file: publish it, talk to it in the browser, then put it on a Twilio phone number. Python, standard library only.
Open-source Golang SDK for Rapida to build real-time, observable Voice AI and voice agents in production systems.
Deepgram SDK integrations with popular platforms, frameworks, and ecosystems maintained by the DX team
TypeScript starter kit for production voice agents: WebRTC, telephony, realtime model APIs, STT/TTS pipelines, barge-in, handoff, evals, and post-call workflows.
Open-source SIP server for StreamCore, connecting PSTN and VoIP calls to realtime AI applications through SIP, RTP and WebRTC.
An AssemblyAI voice agent is one JSON file: publish it, talk to it in the browser, then put it on a Twilio phone number. Node, zero dependencies.
Self-hosted real-time voice agent platform: Pipecat runtime, local Whisper and Kokoro, provider switching, per-conversation latency and cost, privacy by default, Indian languages.
Run AI agent evaluations in your CI/CD pipeline using Calibrate and catch regressions