Google Gemini Live

Overview

Google’s Gemini Live API runs a low-latency, native-audio dialog agent. The bridge proxies Teler call audio into Gemini and relays the model’s spoken response back.

The bridge resamples Gemini’s 24 kHz audio down to Teler’s 8 kHz by default (or up to 16 kHz if you configure your Stream flow for higher fidelity), and lets you tune input buffering to trade off latency against smoother turn-taking.

Key Features

• Reference implementations in Python and Node – Clone teler-gemini-bridge (Python) or teler-gemini-node-bridge (Node) and get a working bridge in minutes.
• One-command Docker setup – Clone the repo, configure your .env, and start with a single command.
• Tunable latency – GEMINI_AUDIO_CHUNK_COUNT controls input buffering, letting you trade off latency against smoother turn-taking.

How to Integrate

Prerequisites

• A Google Cloud project with Gemini API access and a GOOGLE_API_KEY (refer to Google Gemini Live docs)
• A Teler account with an active API key
• One Teler phone number on your account
• An ngrok auth token (for local development)
• Docker and Docker Compose

Step 1: Clone and configure

git clone https://github.com/frejun-tech/teler-gemini-bridge
cd teler-gemini-bridge
cp .env.example .env
docker compose up -d --build

Step 2: Initiate a call

curl -X POST http://your-domain.com/api/v1/calls/initiate-call \
  -H "Content-Type: application/json" \
  -d '{
    "from_number": "+91XXXXXXXXXX",
    "to_number":   "+91XXXXXXXXXX"
  }'

Integration at a Glance