The Video Signal

Topic

Documentation

All digests tagged Documentation

Build a live translation broadcast app with the Gemini Live API and LiveKit thumbnail

· 1:34

Build a live translation broadcast app with the Gemini Live API and LiveKit

This technical demonstration outlines the architecture for a real-time, multilingual broadcast application using the Gemini 3.5 Live Translate API. The system leverages LiveKit and Google Cloud Run to manage long-running WebSocket connections, enabling scalable, real-time speech translation and caption broadcasting via WebRTC data channels.

Key takeaways

  1. Real-Time Multilingual Broadcast

    The application uses Gemini 3.5 Live Translate to set up and manage live translation sessions for multiple languages, subscribing listeners to existing sessions rather than creating new ones for every request.

  2. Scalable WebSockets with Cloud Run

    Deploying Next.js to Google Cloud Run allows the application to maintain long-running WebSocket connections, which is critical for real-time communication.

  3. WebRTC for Captioning

    WebRTC data channels are utilized to broadcast captions alongside the audio stream, enhancing the real-time user experience.

Watch on YouTube Full article

Build a live translation broadcast app with the Gemini Live API and LiveKit thumbnail

· 12:37

Build a live translation broadcast app with the Gemini Live API and LiveKit

This guide details building a real-time multilingual broadcast application using Gemini 3.5 Live Translate via the Gemini API, integrated with LiveKit and deployed on Google Cloud Run. The system efficiently manages multiple language streams by ensuring only one active translation session exists per target language, subscribing new listeners to existing sessions rather than creating redundant ones. The architecture leverages WebSockets for persistent connections and utilizes Next.js for deployment.

Key takeaways

  1. Efficient Session Management 0:58

    The application maintains a maximum of one session per requested target language, subscribing subsequent listeners to the existing LiveGenkit room rather than spinning up new sessions (demonstrated at 0:58).

  2. Deployment Architecture 1:59

    The solution uses Next.js deployed on Google Cloud Run, which allows for hosting long-running WebSockets and managing the necessary stateful connections (1:39).

  3. Scaling Limitations 3:20

    The current demo manages translation details in memory, limiting it to a single Cloud Run instance. Scaling beyond this requires externalizing state management using a database (3:20).

Watch on YouTube Full article

/goal: Building big features with dcode thumbnail

· 8:02

/goal: Building big features with dcode

The video introduces `dcode`, an open-source, model-agnostic coding agent, and its new `/goal` command. This feature enables long-running, persistent tasks by wrapping the standard agent loop in a 'goal loop.' Instead of relying on single-shot requests for large features (like meaty PRs), `/goal` establishes visible acceptance criteria that guide the agent's work over hours. The demonstration shows how to use this mechanism to add native browser control to `dcode`, allowing the user to steer, amend requirements, and inspect progress using tools like LangSmith tracing.

Key takeaways

  1. The /goal Command 2:50

    The `/goal` command provides a long-running, persistent objective for agents tackling large tasks. It shifts alignment work upfront, making it visible and allowing mid-run tailoring of requirements (3:46).

  2. Goal Loop Mechanism 0:35

    The goal loop wraps the agent's inner action loop. The outer loop continuously checks if actions satisfy the durable acceptance criteria; if not, the goal remains active until evidence satisfies all requirements (0:17).

  3. Steering and Amending Goals 4:40

    Users can inspect the current state with `/goal show` or update/correct requirements mid-run using `/goal amend`, which interprets the message within the context of the active goal (3:46).

Watch on YouTube Full article