We just pushed laughter, cough, and emotional control tagging.
onebigname
•
May 20, 2025
Can I drop a video of me laughing
Michael Lingelbach
Team•
Jan 21, 2025
Can you try uploading audio of the laugh? Unfortunately there’s not a good audio synthesis model that does laughter.
Ana Diaz
•
Dec 27, 2024
Please I beg for end a video on the same initial image
1
I would be very glad if there was a possibility (perhaps as an Y/N option) to end a video on the same initial image, so that multiple videos can be tied together without noticeable gaps.
Michael Lingelbach
Team•
Dec 27, 2024
Why do you need multiple videos to be tied together? Are 12 minute videos not long enough?
Ana Diaz
•
Jan 17, 2025
Thanks for your answer. I need to make an adaptation according my possible answers. The answers have a part in common. The end of the answer is a short part but different from the rest. The system would be too heavy if I had to do the total number of videos according each possibility. So, please, I beg your understanding and I hope my request could be real. Thank you very much for your attention.
Michael Lingelbach
Team•
Sep 13, 2024
That’s unfortunately difficult for us to do since we rely on upstream vendors like eleven or cartesia for our voices. Do you know of a good voice synthesis system that deals with this?
Fernando Fiorenzano
•
Sep 13, 2024
There are some TTSs that do this, from what I have read: Amazon Polly TTS service, which has a function called “Speech Marks,” Mozilla TTS engine, which includes a function called “Visemes.”
Log in to comment and vote
Comments8
Michael Lingelbach
Nov 30, 2025
We just pushed laughter, cough, and emotional control tagging.
onebigname
May 20, 2025
Can I drop a video of me laughing
Michael Lingelbach
Jan 21, 2025
Can you try uploading audio of the laugh? Unfortunately there’s not a good audio synthesis model that does laughter.
Ana Diaz
Dec 27, 2024
Please I beg for end a video on the same initial image
1
I would be very glad if there was a possibility (perhaps as an Y/N option) to end a video on the same initial image, so that multiple videos can be tied together without noticeable gaps.
Michael Lingelbach
Dec 27, 2024
Why do you need multiple videos to be tied together? Are 12 minute videos not long enough?
Ana Diaz
Jan 17, 2025
Thanks for your answer. I need to make an adaptation according my possible answers. The answers have a part in common. The end of the answer is a short part but different from the rest. The system would be too heavy if I had to do the total number of videos according each possibility. So, please, I beg your understanding and I hope my request could be real. Thank you very much for your attention.
Michael Lingelbach
Sep 13, 2024
That’s unfortunately difficult for us to do since we rely on upstream vendors like eleven or cartesia for our voices. Do you know of a good voice synthesis system that deals with this?
Fernando Fiorenzano
Sep 13, 2024
There are some TTSs that do this, from what I have read: Amazon Polly TTS service, which has a function called “Speech Marks,” Mozilla TTS engine, which includes a function called “Visemes.”
I also found the page https://www.acapela-group.com/voices/vocal-smileys-examples/ where there are examples of various sounds, like #LAUGH01#. To give it a try go down the page to “Select language+voice to hear voice smileys.”
But I guess using a different system than the current ones may create more problems than it solves...