API audio: occasional volume drop?
by•
Hey @ElevenLabs! The voice quality is miles ahead of anything else we've tried. Huge fan of what you guys are building! 🚀 We’re actually using it in our internal tool to generate audio summaries of specific Spotify topics. It works like magic, but we’ve noticed one tiny hiccup: the audio occasionally fades out or loses volume mid-sentence. Has anyone else experienced this, or is there a specific API parameter we should look into to keep it consistent? Keep up the great work, looking forward to seeing where you take the product next! 👊
106 views
Replies
Hi! Can you specify what exactly model do you use in api (is it model v2 ?) ? I probably do have answer !
@ilia_ilinskii Spot on! Yes, we are using model v2. Would love to hear your thoughts on this – is there a specific stability or clarity setting we should be tweaking for v2 to avoid those drops? Thanks for jumping in!
@tereza_hurtova I faced the same issue with that model generation. The thing helped me was Request Stitching function. I think I can not place link here but you can easily find it by name.
@ilia_ilinskii That’s a goldmine, Ilia, thank you! I haven't come across the Request Stitching function yet, but it sounds exactly like the fix we may need. Going to dive into the documentation right away!
Just curious – are you sticking with v2 as well, or have you moved on to v3 already? And what kind of use case are you using EL for, if it's not a secret? :)
@tereza_hurtova I am using both of them in my meditation app. I really love model_v3, but it is much slower, so I am providing end user to select - Best but slow or Good and Fast options.