멀티채널 텍스트 음성 변환

from elevenlabs import ElevenLabs
elevenlabs = ElevenLabs(api_key="YOUR_API_KEY")
def transcribe_multichannel(audio_file_path):
    with open(audio_file_path, 'rb') as audio_file:
        result = elevenlabs.speech_to_text.convert(
            file=audio_file,
            model_id='scribe_v2',
            use_multi_channel=True,
            diarize=False,
            timestamps_granularity='word'
        )
    return result
# Process the response
result = transcribe_multichannel('stereo_interview.wav')
if hasattr(result, 'transcripts'): # Multichannel response
    for transcript in result.transcripts:
        channel = transcript.channel_index
        text = transcript.text
        print(f"Channel {channel} (speaker_{channel}): {text}")
    else: # Single channel response (fallback)
        print(f"Text: {result.text}")

def process_large_multichannel_file(file_path, chunk_duration=300):
    """Process large files in chunks (5-minute segments)"""
    from pydub import AudioSegment
    from elevenlabs import ElevenLabs
    import os
    elevenlabs = ElevenLabs(api_key="YOUR_API_KEY")
    audio = AudioSegment.from_file(file_path)
    duration_ms = len(audio)
    chunk_size_ms = chunk_duration * 1000
    all_transcripts = []
    for start_ms in range(0, duration_ms, chunk_size_ms):
        end_ms = min(start_ms + chunk_size_ms, duration_ms)
        # Extract chunk
        chunk = audio[start_ms:end_ms]
        chunk_file = f"temp_chunk_{start_ms}.wav"
        chunk.export(chunk_file, format="wav")
        # Transcribe chunk using SDK
        with open(chunk_file, 'rb') as audio_file:
            result = elevenlabs.speech_to_text.convert(
                file=audio_file,
                model_id='scribe_v2',
                use_multi_channel=True,
                diarize=False,
                timestamps_granularity='word'
            )
        # Adjust timestamps
        if hasattr(result, 'transcripts'):
            for transcript in result.transcripts:
                for word in transcript.words or []:
                    word.start += start_ms / 1000
                    word.end += start_ms / 1000
            all_transcripts.extend(result.transcripts)
        # Clean up
        os.remove(chunk_file)
    return all_transcripts