Gemini 3.5 Transcribe Preview is Google's speech to text model, starting at $2.50 / 1M input and $12.00 / 1M output. A Gemini-based speech transcription model that converts audio to text, offered as a preview release.
Specifications
Canonical IDgoogle-gemini-3-5-transcribe-preview
TypeSpeech to Text
StatusActive
CreatorGoogleGoogle
Providers
Input ModalitiesAudioText
Output ModalitiesText

Capabilities

Input2/5
Text
Image·
Audio
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Audio In
$ / 1M
Google Vertex AI logo
Google Vertex AI
vertex_ai/gemini-3.5-transcribe-preview
$2.50$12.00$2.50

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Gemini 3.7 Flash1.0M$0.750$3.75Available
Gemini 3.6 Flash1.0M$0.750$3.75Available
Gemini 3.5 Flash Lite1.0M$0.150$1.25Available
Gemini 3.1 Flash Lite Image66K$0.250$1.50Available
Gemini 3 Pro Image131K$2.00$12.00Available
Gemini 3.1 Flash Image131K$0.500$3.00Available
Gemini 3.5 Flash1.0M$0.750$4.50Available
Gemini 3.1 Flash Lite1.0M$0.250$1.50Available
Gemini 3.1 Flash Lite Preview1.0M$0.250$1.50Deprecated
Gemini 3.1 Pro Preview1.0M$2.00$12.00Available
Gemini 3.5 Transcribe Preview$2.50$12.00Current

Model IDs

['gemini-3.5-transcribe-preview', 'gemini-3.5-transcribe-live-preview']
google-gemini-3-5-transcribe-preview
vertex_ai/gemini-3.5-transcribe-preview