The quality of the generated facial animations will depend on the clarity of the recorded audio.
Follow these recommendations to improve the animation results:
| Recommendation | Configuration |
|---|---|
A minimum 16kHz sampling rate | Lower sampling rates will remove important speech related frequencies from the signal. |
Minimize background noise | Audio with a higher signal-to-noise ratio will result in cleaner animations. |
Avoid reverb and echoes | The animation quality will be reduced if these effects are present in the recording. |
One speaker per audio file | The feature will animate to all voices present in the recording, so having multiple speakers or background voices could affect the resulting animation. |
Next Up
Realtime Animation Guidelines
Guidelines for capturing video for real-time animation.