<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/google-ai-edge/mediapipe/blob/master/mediapipe/tasks/python/audio/text_to_speech.py#L290-L323) |

Computes prosody- and waveform-aligned word timestamps via the C API.

    mp.tasks.audio.compute_word_timestamps(
        text: str,
        num_samples: int,
        sample_rate_hz: int,
        time_offset_sec: float = 0.0,
        samples: Optional[np.ndarray] = None
    ) -> tuple[WordTimestamp, ...]