For Developers/Models/Gemini 3.5 Transcribe
Closed SourcePreviewGoogleReleased 2026-08

Gemini 3.5 Transcribe

The most precise speech-to-text model yet

Context window

Not announced

Input / 1M tokens

$0.003/min

Output / 1M tokens

$0.002/min

Provider

Google

Data verified 2026-08-27

<cite index="6-2">Google's most precise speech-to-text model, designed for intelligent voice interactions.</cite> <cite index="6-1">Unlike conventional speech recognition models that struggle with background noise, complex jargon, and disfluency cleanup, Gemini 3.5 Transcribe converts raw audio directly into accurate, polished, formatted text.</cite>

Capability index

Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.

Coding
0
Reasoning
0
Math
0
Multimodal
1
Long context
0
Speed
1
Cost efficiency
1

How to access it

Available in public preview via Gemini API in Google AI Studio and Gemini Enterprise Agent Platform. Also available in Gemini app on macOS and Gboard on Android.

Strengths

  • Supports 85+ languages with accent and dialect handling
  • Removes filler words and handles self-corrections automatically
  • Speaker attribution and word-level timestamps for up to 3 speakers
  • Custom vocabulary recognition
  • Function calling for delegating tasks to other Gemini models

Best for developers who...

Real-time voice agents and applicationsPost-call analytics and meeting transcriptionMultilingual voice interactionsBuilding voice-enabled applications

When to choose it (and when not to)

Reach for Gemini 3.5 Transcribe when...

  • When you need accurate transcription with speaker attribution
  • For multilingual applications requiring 85+ language support
  • When building voice agents with function calling capabilities

Look elsewhere if...

  • If you need a general-purpose LLM rather than a specialized speech-to-text model
  • For use cases requiring offline processing

How to use it

Quickstart

Python
import anthropic
# Use Gemini API for transcription via Google AI Studio or Enterprise Platform

Accessible through Gemini API in Google AI Studio and Gemini Enterprise Agent Platform

API model id: gemini-3.5-transcribe

Benchmarks

BenchmarkScoreNotes
FLEURS (multilingual)5.50% WER (streaming), 5.04% WER (non-streaming)Across top languages and locales, improving over Chirp 3
Artificial Analysis measurement4.0% WER (streaming), 2.6% WER (non-streaming)On diverse real-world conditions including background noise

Source: Google Official Announcement

Compare Gemini 3.5 Transcribe

Compare Gemini 3.5 Transcribe with any other model

Build a comparison →
All model comparisons →

Learn the concepts