
LiveKit Agents
8.6#1 in conversational ai platformsFrom $50 a monthFree planAndroidiOSWebAPI
Visit

| Fact | LiveKit Agents | Tone |
|---|---|---|
| Headquarters | San Francisco, California, United States | Bengaluru and San Francisco |
| Integrations | LiveKit Inference provides models from providers including OpenAI, Google, AssemblyAI, Deepgram, Cartesia, and ElevenLabs, while open source plugins connect to additional providers. | Listed integrations include OpenAI, Anthropic, Google Gemini, Mistral, Llama, ElevenLabs, Cartesia, PlayHT, Deepgram, Whisper, AssemblyAI, Twilio, Telnyx, Plivo, LiveKit, HubSpot, Salesforce, Zapier, n8n, Slack, Notion, Confluence, and GoHighLevel. |
| Observability | LiveKit Cloud includes transcripts, traces, session recordings, and logs for agent sessions, while self-hosted deployments can use OpenTelemetry hooks. | Observability includes interruption rate, latency, sentiment, gibberish detection, stereo recordings, waveform inspection, custom dashboards, and real-time alerts. |
| Self-hosting | Organizations can run LiveKit servers and Agents on local machines, virtual machines, Kubernetes, or distributed multi-region infrastructure. | Tone can be started with Docker Compose and includes a Kubernetes Helm chart, with Postgres, Redis, and ClickHouse in the example stack. |
It suits developers building realtime voice, video, or multimodal agents who want deployment options and integrations. Teams connecting agents to phone systems can use native SIP support.
Tone suits developers and teams building voice agents across phone, web-widget, or chat channels. Its self-hosting and workflow tools may also suit organizations that want control over deployment and agent logic.