Duygu TTS Filmi: Anlatılarınızı Daha Duygusal Hale Getirin

clip = VideoFileClip(video_path)
clip.audio.write_audiofile(audio_path, codec='pcm_s16le', logger=None)

resp = requests.post(ELEVENLABS_URL, headers={'xi-api-key': ELEVENLABS_KEY}, files={'file': ('audio.wav', f, 'audio/wav')}, data={'model_id': 'scribe_v1'})

def build_emotional_ssml(text: str) -> str:
    return f'''<speak version='1.0' xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='https://www.w3.org/2001/mstts' xml:lang='en-US'>
  <voice name='{voice}'>
    <mstts:express-as style='advertisement_upbeat' styledegree='2'>
      <prosody rate='+15%' pitch='+8%' volume='+15%'>
        {escaped}
      </prosody>
    </mstts:express-as>
  </voice>
</speak>'''

headers = {'Ocp-Apim-Subscription-Key': AZURE_API_KEY, 'Content-Type': 'application/ssml+xml', 'X-Microsoft-OutputFormat': 'riff-24khz-16bit-mono-pcm'}
resp = requests.post(AZURE_TTS_URL, headers=headers, data=ssml.encode('utf-8'), timeout=30)

def concat_wavs(wav_paths: list[str], out_path: str) -> None:
    params = None
    frames = []
    for p in wav_paths:
        if not os.path.exists(p):
            continue
        with wave.open(p, 'rb') as wf:
            if params is None:
                params = wf.getparams()
            frames.append(wf.readframes(wf.getnframes()))
    if not frames:
        logger.warning('Birleştirilecek WAV çerçevesi yok.')
        return
    with wave.open(out_path, 'wb') as out_wf:
        out_wf.setparams(params)
        for f in frames:
            out_wf.writeframes(f)

cmd = ['ffmpeg', '-y', '-i', video_path, '-i', audio_path, '-map', '0:v:0', '-map', '1:a:0', '-c:v', 'copy', '-c:a', 'aac', '-b:a', '192k', '-shortest', out_path]