Daily.co

Daily is a WebRTC infrastructure provider for video and audio calls, and Deepgram is the recommended speech provider inside the Daily ecosystem. Live transcription, meeting summaries, voice agent pipelines, and live captions all run on Deepgram models behind a few lines of Daily SDK configuration.

For product teams, this matters because adding real-time voice intelligence to a video product (telehealth, customer support, recruiting, training) usually means evaluating a transcription vendor, building an audio routing layer, and writing reconciliation logic. Daily and Deepgram remove most of that. The audio is already streaming through Daily; pointing it at Deepgram is one configuration step: pass enable_transcription with the value "Deepgram:<your API key>" and live transcription is enabled at the account level.

Real-time streaming uses WebSockets so new audio streams to Deepgram while the latest transcription results stream back, full duplex. The pattern supports live captions for accessibility, real-time meeting transcription with diarization, and any use case where latency matters.

For voice agents specifically, Pipecat (Daily's open-source voice agent framework) ships with native Deepgram services. It's the production path from a working prototype to a deployed agent.

If you are building on Daily and want voice intelligence, the integration walks through the SDK property in a few minutes. For voice agents, see the Pipecat partner page.

• Daily.co partner page
• Add Live Transcriptions to a Daily Video Call with Deepgram (Built with Deepgram)
• Video: Add Live Transcriptions to a Daily Video Call With Deepgram
• Transcribe Meetings in Realtime (developer docs)
• Pipecat (Daily's voice agent framework, GitHub)
• Daily WebRTC API
• Deepgram documentation
• Contact Deepgram