Audio

pip install "apertis>=0.4.0"

from apertis import Apertis

def main():
    client = Apertis()

    with open("audio.mp3", "rb") as audio_file:
        response = client.audio.transcriptions.create(
            model="whisper-1",
            file=audio_file
        )

    print(response.text)

if __name__ == "__main__":
    main()

from apertis import Apertis

def main():
    client = Apertis()

    with open("audio.mp3", "rb") as audio_file:
        response = client.audio.transcriptions.create(
            model="whisper-1",
            file=audio_file,
            language="en",           # Specify language for better accuracy
            prompt="Technical discussion about AI and machine learning",  # Context hint
            response_format="verbose_json",  # Get detailed output
            temperature=0.0          # Lower = more deterministic
        )

    print(f"Text: {response.text}")

    # verbose_json fields such as segments are kept as plain dicts
    for segment in response.model_dump().get("segments", []):
        print(f"  [{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}")

if __name__ == "__main__":
    main()

from apertis import Apertis

def main():
    client = Apertis()

    # Translate non-English audio to English text
    with open("spanish_audio.mp3", "rb") as audio_file:
        response = client.audio.translations.create(
            model="whisper-1",
            file=audio_file
        )

    print(f"English translation: {response.text}")

if __name__ == "__main__":
    main()

from apertis import Apertis

def main():
    client = Apertis()

    response = client.audio.speech.create(
        model="gpt-4o-mini-tts-2025-12-15",
        voice="alloy",
        input="Hello! Welcome to Apertis AI. How can I help you today?"
    )

    response.write_to_file("output.mp3")

    print("Audio saved to output.mp3")

if __name__ == "__main__":
    main()

from apertis import Apertis

def main():
    client = Apertis()

    response = client.audio.speech.create(
        model="gpt-4o-mini-tts-2025-12-15",
        voice="nova",            # Different voice
        input="This is text-to-speech audio with a different voice.",
        response_format="opus",  # Opus format for better quality
        speed=1.0                # Normal speed (0.25 to 4.0)
    )

    response.write_to_file("output.opus")

    print("Audio saved to output.opus")

if __name__ == "__main__":
    main()

import os
from openai import OpenAI

def main():
    client = OpenAI(api_key=os.environ["APERTIS_API_KEY"], base_url="https://api.apertis.ai/v1")

    with client.audio.speech.with_streaming_response.create(
        model="gpt-4o-mini-tts-2025-12-15",
        voice="shimmer",
        input="This audio is being streamed as it's generated.",
    ) as response:
        response.stream_to_file("streamed_output.mp3")

    print("Streamed audio saved to streamed_output.mp3")

if __name__ == "__main__":
    main()

import base64
from apertis import Apertis

def main():
    client = Apertis()

    # Read and encode audio file
    with open("question.mp3", "rb") as f:
        audio_data = base64.standard_b64encode(f.read()).decode("utf-8")

    response = client.chat.completions.create(
        model="gpt-4o-audio-preview",
        messages=[
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": "Please respond to this audio message:"},
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": audio_data,
                            "format": "mp3"
                        }
                    }
                ]
            }
        ]
    )

    print(response.choices[0].message.content)

if __name__ == "__main__":
    main()

import asyncio
from pathlib import Path
from apertis import AsyncApertis

async def transcribe_file(client: AsyncApertis, file_path: str) -> dict:
    """Transcribe a single audio file."""
    with open(file_path, "rb") as f:
        response = await client.audio.transcriptions.create(
            model="whisper-1",
            file=f
        )
    return {"file": file_path, "text": response.text}

async def main():
    client = AsyncApertis()

    # List of audio files to process
    audio_files = list(Path("audio_folder").glob("*.mp3"))

    # Process files concurrently
    tasks = [transcribe_file(client, str(f)) for f in audio_files]
    results = await asyncio.gather(*tasks)

    for result in results:
        print(f"\n{result['file']}:")
        print(f"  {result['text'][:100]}...")

if __name__ == "__main__":
    asyncio.run(main())