Voice Cloned TTS Inference

Example request

{
  "text": "नमस्ते, आप कैसे हैं?",
  "model": "vachana-vc-v1",
  "speaker_embedding": {
    "embedding": "<base64-encoded embedding>",
    "shape": [
      1,
      768
    ],
    "dtype": "torch.bfloat16"
  },
  "audio_config": {
    "sample_rate": 44100,
    "num_channels": 1,
    "sample_width": 2,
    "encoding": "linear_pcm",
    "container": "wav"
  }
}