Gemini 3.5 Transcribe

Transcriptions

gemini-3.5-transcribe

Google|Created Oct 30, 2026

Transcriptions

Gemini 3.5 Transcribe is a speech-to-text model based on Gemini's audio understanding capabilities. It provides low-latency, accurate transcription with utterance-based language detection, speaker diarization, word-level timestamps, Smart transcription, and custom vocabulary speech biasing.

Overview Specifications Activity Performance Uptime Examples API Reference

Compare

Pricing-50%

Pay-as-you-go rates for this model. More details in the billing guide.

Transcription (1 minute)

$0.0015

Capabilities

Gemini 3.5 Transcribe API Provider | NagaAI

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(base_url="https://api.naga.ac/v1", api_key="YOUR_API_KEY")

with open("audio.mp3", "rb") as f:
    transcription = client.audio.transcriptions.create(
        model="gemini-3.5-transcribe",
        file=f,
        prompt=None,
        language=None,
    )
print(transcription.text)

Gemini 3.5 Transcribe

Transcription (1 minute)

Gemini 3.5 Transcribe

Transcription (1 minute)

Input Modalities

Output Modalities