Voice Agents Latency Benchmark
Compare latency performance across different voice agent platforms. Lower latency means faster, more natural conversations.
Results obtained from running our automated test suite from EU region and with the default configuration of each Platform. Click any row to get some additional information about the test conditions.
Latency measurements represent the complete round-trip time from when a user stops speaking until they hear the agent's response begin. This includes audio processing at both ends, turn detection, STT, LLM, TTS, network transmission delays and any delay introduced by each platform.
The test suite ran for these tests was the basic one without tools calling or complex scenarios.
For other test suites, regions, full report or custom tests please reach out to contact@livetok.io.
Platform | STT | LLM | TTS | Latency | |
---|---|---|---|---|---|
VAPI | Deepgram | OpenAI | ElevenLabs | ~1350ms | |
Retell AI | Deepgram | OpenAI | ElevenLabs | ~1250ms | |
OpenAI RealTime | N/A | OpenAI | N/A | ~1400ms | |
LiveTok Gemini | Deepgram | OpenAI | ElevenLabs | ~1350ms | |
LiveKit | Deepgram | OpenAI | ElevenLabs | ~1800ms | |
Pipecat | Deepgram | OpenAI | ElevenLabs | ~1800ms |