
Voice pipeline for AI agents
Cloudflare's experimental voice pipeline for Agents SDK enables real-time voice over WebSockets. It supports continuous STT and TTS. Developers can implement it in ~30 lines of server-side code.
Few direct matches — filled in with the latest updates.
Tag: #stt-tts3 results

Cloudflare's experimental voice pipeline for Agents SDK enables real-time voice over WebSockets. It supports continuous STT and TTS. Developers can implement it in ~30 lines of server-side code.

Speechos is an open-source tool for side-by-side benchmarking of local STT, TTS, emotion detection, and diarization models. Supports 25+ engines like faster-whisper, Piper, Bark, and Qwen3-TTS, with hardware-adaptive setups from CPU to GPU. MIT-licensed GitHub repo includes dev script for quick setup.

Together AI now enables building real-time voice agents using co-located STT, LLM, and TTS infrastructure. It offers native support for Deepgram and Cartesia providers. End-to-end latency is under 700ms for responsive interactions.

Google is adding an AI chatbot interface that lets users describe the content they want in their Discover feed. The feature will automatically adjust feed recommendations and remember preferences for future visits.

Amazon Bedrock now supports OpenAI GPT-5.6 models—Sol, Terra, and Luna—across more than 25 AWS Regions through cross-Region inference. Developers can use US geographic or global inference profiles to improve throughput and access the models through OpenAI and Converse APIs.
OpenClaw released a fix to ensure its release process trusts exact protected tooling tags. The change addresses release-publishing behavior and improves tag validation reliability.
Slack announced Slack Code, a feature that lets teams collaborate with AI coding agents through dedicated code channels. Users can review plans, code diffs, and previews, then approve actions from agents such as Claude and Devin.

ChatGPT's latest Mac update integrates with Apple Messages, allowing users to bring conversations from Apple's messaging app into the AI assistant. The feature expands ChatGPT's access to personal communication workflows on macOS.

Part 1 shows how to configure an AWS account and Snowflake environment for a no-code machine learning workflow. The setup prepares healthcare, retail, and life sciences teams to build a fraud detection model with Amazon SageMaker Canvas.
Google’s Magic Capture automatically extracts photos from video footage, helping users save spontaneous moments without manually scrubbing through clips. An early test with an uncooperative cat demonstrates the feature’s potential for computational photography and everyday image capture.