Forge is available: build a website with AI from your RodiumAi account.

Try Forge
Google

Gemini 3.5 Transcribe Live

google/gemini-3.5-transcribe-live

transcriptionsttaudioliverealtimepreview

Input price

2637.4 RODI/M

~ 3.5 USD/M

Output price

15824.3 RODI/M

~ 21 USD/M

Context

—

Max output

—

Input:audio
Output:text

Providers & pricing

ProviderInputOutputFree tier
Vertex

Vertex

Default

2637.4 RODI/M~3.50 USD/M15824.3 RODI/M—
Google AI Studio

Google AI Studio

2637.4 RODI/M~3.50 USD/M15824.3 RODI/M—

Pricing

RateRODIUSD (ref.)Unit
In2637.4~ 3.50USD/M · RODI/M
Out15824.3~ 21.00USD/M · RODI/M
Audio in—~ 3.50USD/s · RODI/s

RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.

Capabilities

Streaming
Tool calling
Vision
JSON mode
Reasoning

About this model

Google real-time streaming speech-to-text via Gemini Live API (WebSocket BidiGenerateContent). Low-latency interim + final transcripts for microphone / streaming audio up to ~10 minutes per session.

API usage

Transcribe audio with client.transcribe() — multipart POST /v1/audio/transcriptions.

RodiumAi SDK

transcribe() uploads a local audio file via multipart form.

…

Compatible SDKs (OpenAI / Anthropic packages)

…