Skip to content

Gemini 3.5 Transcribe now available on AI Gateway

,

Gemini 3.5 Transcribe from Google is now available on AI Gateway for recorded and live audio:

  • google/gemini-3.5-transcribe transcribes a complete audio file in one request.

  • google/gemini-3.5-transcribe-live transcribes audio over a WebSocket and returns text as the audio arrives.

Both models automatically detect more than 85 languages, including when a speaker switches languages. You can also provide custom vocabulary to improve the transcription of names, technical terms, and uncommon spellings. The model for complete recordings can also identify speakers and return word-level timestamps.

Streaming transcription is available in AI SDK 7. Install the latest AI SDK and AI Gateway provider: 

npm install ai@latest @ai-sdk/gateway@latest

Install the packages required for streaming transcription.

Copy link to headingTranscribe live audio

Use streamTranscribe with a ReadableStream of raw audio chunks. Set inputAudioFormat to match the audio being sent: 

import { gateway } from '@ai-sdk/gateway';
import { experimental_streamTranscribe as streamTranscribe } from 'ai';


const result = streamTranscribe({
  model: gateway.transcription('google/gemini-3.5-transcribe-live'),
  audio: microphoneStream, // ReadableStream of 16 kHz, 16-bit PCM chunks
  inputAudioFormat: { type: 'audio/pcm', rate: 16000 },
  providerOptions: {
    google: { mode: 'SMART' }, // or 'VERBATIM' (default)
  },
});

Stream transcript updates as live audio arrives.

Copy link to headingTranscribe a complete recording

Use transcribe to send a complete audio file and receive the finished transcript:

import { gateway } from '@ai-sdk/gateway';
import { experimental_transcribe as transcribe } from 'ai';
import { readFile } from 'node:fs/promises';


const result = await transcribe({
  model: gateway.transcriptionModel('google/gemini-3.5-transcribe'),
  audio: await readFile('meeting.mp3'),
});
console.log(result.text);

Transcribe a complete audio file in one request.

Try Gemini 3.5 Transcribe Live in the model playground, browse all transcription models, or read the speech quickstart.