deepgram

Deepgram acquires Daily, maker of the popular open-source voice AI framework Pipecat, to strengthen its real-time voice AI infrastructure, while committing to keep Pipecat open-source and launching a new Real-Time Context Standard protocol for voice agents.

Deepgram's new Flux TTS targets a critical accuracy bottleneck in voice-agent pipelines, achieving a 3.4% word error rate on tricky alphanumeric strings like medication names and tracking numbers while preserving natural-sounding speech through the full voice loop.

A sponsored post comparing REST, GraphQL, gRPC, and WebSockets, then introducing Deepgram Flux TTS — a conversation-aware text-to-speech API for real-time voice agents with built-in interruption handling, sub-80ms latency, and VPC/on-prem deployment.

A developer describes a failure mode in AI phone agents where the agent stalls mid-call without errors, causing dropped calls and turn-taking issues, and seeks diagnostic advice.

A tutorial demonstrating a low-latency voice agent setup with Pipecat PhoneLLM Alpha 1 on Modal, using Deepgram transcription and Cartesia voice, with code and video guides.

Deepgram released Flux TTS, a streaming conversation-native text-to-speech model that retains tone, pacing, and context across turns, handles interruptions, and runs with latency as low as 80ms to make voice AI feel more natural.