Google Gemini Live

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.

Reference repos

Python teler-gemini-bridge

Node teler-gemini-node-bridge

Prerequisites

A Google Cloud project with Gemini API access and a GOOGLE_API_KEY
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

Configuration

Variable	Required	Default	Description
`GOOGLE_API_KEY`	yes	none	Your Google API key with Gemini access.
`GEMINI_MODEL`	no	`gemini-2.5-flash-preview-native-audio-dialog`	Model identifier.
`GEMINI_SYSTEM_MESSAGE`	no	none	System prompt that defines the agent’s persona and behavior.
`GEMINI_AUDIO_CHUNK_COUNT`	no	`5`	How many chunks to buffer before forwarding to Gemini.
`TELER_API_KEY`	yes	none	Your Teler API key.
`NGROK_AUTHTOKEN`	yes (local)	none	ngrok auth token.
`SERVER_DOMAIN`	auto	none	Public URL exposed to Teler. Detected from ngrok.

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

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

Initiate a call

curl -X POST http://localhost:8000/api/v1/calls/initiate-call \
  -H "Content-Type: application/json" \
  -d '{
    "from_number": "+91XXXXXXXXXX",
    "to_number":   "+91XXXXXXXXXX"
  }'

Audio quirks

Gemini Live emits 24 kHz PCM. The bridge resamples to 8 kHz for Teler using scipy. If you need higher fidelity, configure your Stream flow with sample_rate: "16k" and adjust the bridge’s downsampling code.

Tuning latency

GEMINI_AUDIO_CHUNK_COUNT controls input buffering. Lower = lower latency but more network overhead and higher token consumption. Higher = smoother turns but laggier feel. The default of 5 is a reasonable starting point.

Troubleshooting

Symptom	Likely cause	Fix
Agent silent	Model name typo or unreleased	Check `GEMINI_MODEL` against current Google docs
API quota errors	Free-tier limits hit	Check usage in Google Cloud Console
Long latency to first token	Cold start	Send a warm-up message before connecting calls
Wrong language / persona	Empty `GEMINI_SYSTEM_MESSAGE`	Set the system prompt explicitly

Next steps

Other recipes OpenAI Realtime, ElevenLabs, Vapi, and more.

Bridge architecture The conceptual model behind every recipe.