---
last_updated: 2026-11-20
source_url: https://opper.ai/google/gemini-3-5-transcribe-live
title: "Gemini 3.5 Transcribe Live by Google"
description: "Gemini 3.5 Transcribe Live, Google's real-time speech-to-text model that streams interim and final transcripts over a WebSocket with sub-second latency, automatic language detection, and built-in voice activity detection."
---

# Gemini 3.5 Transcribe Live

By [Google](https://opper.ai/google).

Released 26 Aug 2026, 13 days after [Gemini 3.7 Flash](https://opper.ai/google/gemini-3-7-flash) · [Announcement](https://ai.google.dev/gemini-api/docs/changelog#08-26-2026) · [All Google releases](https://opper.ai/model-releases/google)

Gemini 3.5 Transcribe Live is the streaming variant of Gemini 3.5 Transcribe, Google's speech-to-text suite released on August 26, 2026. It runs on the Gemini Live API as gemini-3.5-transcribe-live: clients stream raw 16-bit, 16kHz mono PCM audio in roughly 100ms chunks and receive speculative interim hypotheses while someone speaks, followed by a finalized transcript when the turn ends. Output is text only.

Turn handling supports automatic server-side voice activity detection, a hybrid mode that finalizes faster using client-side silence detection, and manual push-to-talk signaling. Google says the model detects language automatically across more than 85 languages, handles live language switching, supports custom vocabulary biasing of up to 1,000 terms, and offers a smart transcription mode that removes filler words and formats text. On Google's numbers, Gemini 3.5 Transcribe averages 4.0% word error rate in streaming (2.6% non-streaming) and is 70% faster than Chirp 3.

Live sessions are capped at 10 minutes and do not include speaker diarization or word-level timestamps, which the non-streaming model offers. It fits voice agents, live captioning, dictation, and voice-driven interfaces that need text as the user talks.

## Available routes

Gemini 3.5 Transcribe Live runs on 2 different routes through the Opper gateway. Prices are per 1M tokens. In the EU it is served by Google Cloud. [See every Gemini model hosted in the EU](https://opper.ai/models/eu/gemini). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=gemini%2Fgemini-3.5-transcribe-live.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Google Cloud](https://opper.ai/provider/google) | `gemini/gemini-3.5-transcribe-live` | US (United States) | Abuse monitoring | No | $3.50 | $21.00 | Input price |
| [Google Cloud](https://opper.ai/provider/google) | `vertexai/gemini-3.5-transcribe-live-eu` | EU | Abuse monitoring | No | $3.50 | $21.00 | Input price |

## Key info

- Model id: `gemini/gemini-3.5-transcribe-live`
- Input: Text, Audio
- Output: Text
- Features: none listed
- Text input price: $3.50 per 1M tokens
- Text output price: $21.00 per 1M tokens
- Audio input price: $3.50 per 1M tokens
- Audio output price: $21.00 per 1M tokens
- Released: 26 Aug 2026
- EU residency available on Google Cloud
- US residency available on Google Cloud
- Zero data retention with abuse monitoring
- No training by default

## Data handling per route

Each route hosting Gemini 3.5 Transcribe Live has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### Google Cloud — United States

Zero data retention with abuse monitoring: prompts and outputs are kept for abuse monitoring only, for a window the provider does not state, and are not used for training. No training on customer data. US; SCCs.

- Zero data retention: With abuse monitoring, window not stated.
- Training: No training on customer data.
- Logging: Abuse monitoring
- Abuse monitoring: On by default, holds flagged content, 55 days, a person can view samples
- Transfer mechanism: SCCs

Verified by Opper on 2026-09-17.

### Google Cloud — EU

Zero data retention with abuse monitoring: nothing is logged or used for training; content flagged by abuse monitoring is held for review. No training on customer data. EU.

- Zero data retention: With abuse monitoring, flagged content held.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: On by default, holds flagged content, 90 days, a person can view samples
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-10-26.

## Get started

Call Gemini 3.5 Transcribe Live through the Opper gateway with one API key. Realtime models run over a WebSocket at wss://api.opper.ai/v3/realtime: open it, send session.start with this model, then stream audio both ways.

See the [Opper realtime quickstart](https://docs.opper.ai/build/realtime/quickstart), the [realtime protocol](https://docs.opper.ai/build/realtime/protocol) and the [Opper multimodal skill](https://skills.opper.ai/opper-multimodal/SKILL.md).

Gemini 3.5 Transcribe Live is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai/opper-multimodal/SKILL.md Start a realtime voice session with Gemini 3.5 Transcribe Live
```

### Or call it directly

Node.js:

```javascript
import WebSocket from "ws";

const ws = new WebSocket("wss://api.opper.ai/v3/realtime", {
  headers: { Authorization: `Bearer ${process.env.OPPER_API_KEY}` },
});

ws.on("open", () => {
  ws.send(JSON.stringify({
    type: "session.start",
    config: {
      model: "gemini/gemini-3.5-transcribe-live",
    },
  }));
});

// Stream microphone audio in with { type: "audio.append", audio: <base64 PCM16> }
ws.on("message", (raw) => {
  const ev = JSON.parse(raw.toString());
  if (ev.type === "transcript.committed") console.log(ev);
});
```

## Use Gemini 3.5 Transcribe Live in your apps

Pick your tool to see how to run it on Gemini 3.5 Transcribe Live through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/gemini-3-5-transcribe-live)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/gemini-3-5-transcribe-live)
- [Codex](https://opper.ai/apps/codex/gemini-3-5-transcribe-live)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/gemini-3-5-transcribe-live)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/gemini-3-5-transcribe-live)
- [Aider](https://opper.ai/apps/aider/gemini-3-5-transcribe-live)
- [Goose](https://opper.ai/apps/goose/gemini-3-5-transcribe-live)
- [Droid](https://opper.ai/apps/droid/gemini-3-5-transcribe-live)
- [OpenCode](https://opper.ai/apps/opencode/gemini-3-5-transcribe-live)
- [Pi](https://opper.ai/apps/pi/gemini-3-5-transcribe-live)
- [OpenClaw](https://opper.ai/apps/openclaw/gemini-3-5-transcribe-live)
- [Hermes](https://opper.ai/apps/hermes/gemini-3-5-transcribe-live)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/gemini-3-5-transcribe-live)
- [OmniRoute](https://opper.ai/apps/omniroute/gemini-3-5-transcribe-live)
- [Cursor](https://opper.ai/apps/cursor/gemini-3-5-transcribe-live)
- [Cline](https://opper.ai/apps/cline/gemini-3-5-transcribe-live)
- [Continue](https://opper.ai/apps/continue/gemini-3-5-transcribe-live)
- [Kilo Code](https://opper.ai/apps/kilo-code/gemini-3-5-transcribe-live)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/gemini-3-5-transcribe-live)
- [Zed](https://opper.ai/apps/zed/gemini-3-5-transcribe-live)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/gemini-3-5-transcribe-live)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/gemini-3-5-transcribe-live)
- [n8n](https://opper.ai/apps/n8n/gemini-3-5-transcribe-live)
- [LibreChat](https://opper.ai/apps/librechat/gemini-3-5-transcribe-live)
- [Open WebUI](https://opper.ai/apps/open-webui/gemini-3-5-transcribe-live)
- [See all apps](https://opper.ai/apps)

## Other models from Google

- [Gemini 4 Argon](https://opper.ai/google/gemini-4-argon)
- [Gemini 3.8 Flash](https://opper.ai/google/gemini-3-8-flash)
- [Gemini 3.5 Flash-Lite](https://opper.ai/google/gemini-3-5-flash-lite)
- [Gemini 3.7 Flash](https://opper.ai/google/gemini-3-7-flash)
- [Gemini 3.6 Flash](https://opper.ai/google/gemini-3-6-flash)
- [Gemini 3.5 Flash](https://opper.ai/google/gemini-3-5-flash)
