from google import genai

client = genai.Client()

# Upload audio file via the Files API
audio_file = client.files.upload(file="path/to/audio.wav")

# Transcribe with speaker diarization and word timestamps
interaction = client.interactions.create(
    model="gemini-3.5-transcribe",
    input=[{
        "type": "audio",
        "uri": audio_file.uri,
        "mime_type": audio_file.mime_type,
    }],
    generation_config={
        "transcription_config": {
            "language_codes": ["en-US"],
            "custom_vocabulary": ["Gemini", "Transcribe"],
            "mode": {
                "type": "verbatim",
                "diarization_mode": "speaker",
                "timestamp_granularities": ["word"],
            }
        }
    }
)

print(interaction.output_text)