#has the speech to text model from elevenlabs a input file size limite in time?

1 messages · Page 1 of 1 (latest)

inner cradleBOT
#
AI-generated Answer for baptiste_57867

Yes, the Speech-to-Speech model (previously known as Voice Changer) has a maximum input length of 300 seconds (5 minutes) per audio file. This limit applies across all subscription plans.

If you need to process longer audio files, you can split them into smaller segments before uploading. Let me know if you need further clarification!

covert verge