79756875

Date: 2025-09-05 14:15:00
Score: 2
Natty:
Report link

You can also get word-level timestamps by using speech-to-text APIs that include timing data in their response. I've used AssemblyAI for this - their API returns timestamps for each word during transcription, so you don't need to run forced alignment as a separate step. This can be simpler if you're starting with just audio and need both the text and timing information.

Reasons:
  • No code block (0.5):
  • Single line (0.5):
  • Low reputation (1):
Posted by: Kelsey Foster