Using Gemini 3.5 Transcribe on GCP Vertex AI
Implementation guide · Gemini 3.5 · Google DeepMind
GCP Vertex AI exposes Gemini 3.5 Transcribe through model ID gemini-3.5-transcribe. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-02. Next refresh: weekly.
Quick Start
- 1
- 2Use the GCP Vertex AI SDK or REST API to call
gemini-3.5-transcribe— see the documentation for request format. - 3
Code Examples
pip install google-cloud-aiplatformGOOGLE_CLOUD_PROJECTgemini-3.5-transcribeFor Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".
import os
import vertexai
from vertexai.generative_models import GenerativeModel
# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("gemini-3.5-transcribe")
response = model.generate_content("Hello")
print(response.text)Pricing on GCP Vertex AI
| Type | Price (per 1M) |
|---|---|
| Output tokens | $12.00 |
| Audio input | $2.50 |
Capabilities
About Gemini 3.5 Transcribe
Gemini 3.5 Transcribe is Google DeepMind's speech-to-text model for audio files. Use gemini-3.5-transcribe for pre-recorded recordings when speaker diarization and word-level timestamps matter; use its documented gemini-3.5-transcribe-live access endpoint through the Live API for continuous, bidirectional streaming transcription. The model accepts audio and text within a 96K-token context and returns text with up to 32K output tokens.