LiveKit Agents vs Stream Video

LiveKit Agents is an open source framework and cloud platform for building voice, video, and physical AI agents. Python or Node.js programs can join LiveKit rooms as realtime participants, and deployments can run on LiveKit Cloud or a developer-chosen environment. Agents can process realtime voice, video, and text input and produce output in any modality. The framework supports LLM tool use, frontend RPC calls, multi-agent handoffs, and connections to phone systems through native SIP. LiveKit Inference provides models from providers including OpenAI, Google, AssemblyAI, Deepgram, Cartesia, and ElevenLabs; open source plugins connect to other providers. LiveKit Cloud includes agent insights such as session replay, transcripts, trace spans, logs, and reports. The free Build plan includes 1,000 agent session minutes, five concurrent sessions, and one deployment. Ship starts at $50 a month and includes 5,000 minutes, then $0.01. LiveKit says prompts, audio, and completions handled by LiveKit Inference and its model providers are not logged or retained. It lists SOC 2 Type II, GDPR, HIPAA, CCPA / CPRA, and the EU–US Data Privacy Framework; PCI DSS and ISO 27001 are in progress.

Stream Video has no write-up on Specifiction yet; its figures are above.