Gemini 3.5 Transcribe

import asyncio
from google import genai
from google.genai import types

client = genai.Client(enterprise=True, project=PROJECT_ID, location=LOCATION)

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    input_audio_transcription=types.AudioTranscriptionConfig(
        language_codes=["it-IT", "en-US"],
    ),
)

async def streaming_main(audio_file, config):
    # Connect to the Live API session
    async with client.aio.live.connect(model="gemini-3.5-transcribe-live", config=config) as session:
        # In a complete implementation, you would chunk the audio and send via:
        # await session.send_realtime_input(audio=types.Blob(data=data, mime_type="audio/pcm;rate=16000"))
        # await session.send_realtime_input(audio_stream_end=True)

        async for message in session.receive():
            if message.server_content:
                server_content = message.server_content

                # Track the active interim segment
                interim = server_content.interim_input_transcription
                if interim and interim.text:
                    print(f"Interim: {interim.text}")

                # Save final transcript and clear the interim
                final = server_content.input_transcription
                if final and final.text:
                    print(f"Final: {final.text}")

from google import genai
from google.genai import types

# Initialize the client for Vertex AI / Agent Platform
client = genai.Client(enterprise=True, project=PROJECT_ID, location=LOCATION)

with open("input.wav", "rb") as f:
    audio_bytes = f.read()

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[
        types.Part.from_bytes(
            data=audio_bytes,
            mime_type="audio/wav",
        ),
    ],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            word_timestamp=True,
        ),
    ),
)

parts = getattr(response, "parts", []) or []
if parts and (audio_tx := getattr(parts[0], "audio_transcription", None)):
    for w in getattr(audio_tx, "words", []) or []:
        print(f"[{w.start_offset} - {w.end_offset}] {w.word}")

if text := "".join(p.text for p in parts if getattr(p, "text", None)):
    print(f"**{text}**")

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[
        types.Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/audio/coffee_order.wav",
            mime_type="audio/wav",
        ),
    ],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            diarization=True,
            language_codes=["en-US"],
            custom_vocabulary=["oatmilk", "oz"],
        ),
    ),
)

parts = getattr(response, "parts", []) or []
for p in parts:
    audio_tx = getattr(p, "audio_transcription", None)
    speaker = getattr(audio_tx, "speaker_label", "UNKNOWN") if audio_tx else "UNKNOWN"
    text = getattr(p, "text", "") or (getattr(audio_tx, "text", "") if audio_tx else "")

    if text:
        print(f"**{speaker}**: {text}")

response = client.models.generate_content(
    model="gemini-3.5-transcribe",
    contents=[
        types.Part.from_bytes(
            data=audio_bytes,
            mime_type="audio/wav",
        ),
    ],
    config=types.GenerateContentConfig(
        audio_transcription_config=types.AudioTranscriptionConfig(
            mode="SMART",
        ),
    ),
)

config = types.LiveConnectConfig(
    response_modalities=["TEXT"],
    realtime_input_config=types.RealtimeInputConfig(
        automatic_activity_detection=types.AutomaticActivityDetection(
            disabled=True,
        ),
    ),
    input_audio_transcription=types.AudioTranscriptionConfig(
        mode="SMART",
    ),
)

async with client.aio.live.connect(
    model="gemini-3.5-transcribe-live", config=config
) as session:
    # Signal start of speech turn
    await session.send_realtime_input(activity_start=types.ActivityStart())

    # Stream audio chunks...
    await session.send_realtime_input(
        audio=types.Blob(data=audio_bytes, mime_type="audio/pcm;rate=16000")
    )

    # Signal end of speech turn so SMART mode can process the complete utterance
    await session.send_realtime_input(activity_end=types.ActivityEnd())