Deepgram Launches Voice Agent API

Deepgram, a voice artificial intelligence platform provider, has launched its Voice Agent API, a single, unified voice-to-voice interface to build context-aware voice agents that power natural, responsive conversations.

Combining speech-to-text, text-to-speech, and large language model (LLM) orchestration with contextualized conversational logic into a unified architecture, the Voice Agent API lets developers use Deepgram's fully integrated stack (leveraging Nova-3 STT and Aura-2 TTS models) or bring their own LLM and TTS models. They retain full control over orchestration, deployment, and model behavior.

Deepgram's Voice Agent API provides a single, unified API with built-in support for real-time conversational dynamics. Capabilities such as barge-in handling and turn-taking prediction are model-driven and managed natively within the platform. It also gives teams deep control over performance, behavior, and scalability in production. Built on Deepgram's Enterprise Runtime and full model ownership across the entire voice AI stack, the platform enables model-level optimization at every layer of the interaction loop. This allows for precise tuning of latency, barge-in handling, turn-taking, and domain-specific behavior.

"The future of customer engagement is voice-first," said Scott Stephenson, CEO of Deepgram, in a statement. "But most voice systems today are rigid, fragmented, or too slow. With our Voice Agent API, we're giving developers a powerful yet simple interface to build conversational agents that feel natural, respond instantly, and scale across use cases without compromise."

In recent benchmark testing using the Voice Agent Quality Index (VAQI), Deepgram achieved the highest overall score among all evaluated providers. VAQI measures the core elements of voice agent quality: latency (how quickly the agent responds), interruption rate (how often it cuts users off), and response coverage (how often it misses valid input). In that testing, Deepgram reportedly outperformed OpenAI by 6.4 percent and ElevenLabs by 29.3 percent.