Audio clipping

import os

from perceptron import Client, audio

client = Client(
    provider="perceptron",
    api_key=os.environ["PERCEPTRON_API_KEY"],
)
audio_part = audio("recording.wav")


def locate_event(question):
    response = client.chat.completions.create(
        model="perceptron-mk1.5",
        messages=[{
            "role": "user",
            "content": [
                audio_part,
                {"type": "text", "text": (
                    question + " Use clip annotations with asset_idx=0 and "
                    "timestamps in explicit seconds from the start of this recording. "
                    "If the event is absent or unclear, say so without inventing timestamps."
                )},
            ],
        }],
        reasoning_effort="high",
        max_completion_tokens=2048,
        vision_config={"annotation_format": "clip"},
    )
    choice = response.choices[0]
    if choice.finish_reason != "stop" or choice.message.tool_calls:
        raise RuntimeError(f"Incomplete audio clipping answer: {choice.finish_reason}")
    return choice.message.content or ""


print(locate_event(
    "Find the first audible alarm. Return an interval from when the alarm "
    "begins until that occurrence stops."
))

print(locate_event(
    "Find the moment the first alarm begins. Return one timestamp for its onset."
))

<clip mention="alarm begins" asset_idx="0" t="2.4 seconds" />
<clip mention="first alarm" asset_idx="0" t="2.4 seconds 5.8 seconds" />