Activity
Mon
Wed
Fri
Sun
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
What is this?
Less
More
10 contributions to AI Automation Agency Hub
ELEVENLABS VOICE ISSUE
hey everyone is anyone has tried the INDIAN name pronunciation using ELEVENLABS As I have tried to speel the Indian names with the exact words written in Devanagari with model turbo v2.5 and rest English words with model multilingual v2 and some English words which is hard to pronounce i was using phoneme with CMU in the model turbo v2 , as that only accepts the phoneme technique . SO my single script generation takes three models to generate , but problem arises here the pitch of every voice is sound different, but the voice is same in all three as I have trained on my voice using PVC Is there any solution for this
3 likes • 3d
@Muhammad Khan but I am using through API and my voice is generated through English , the issue here is I am passing the language code "hi" using turbo v2.5 with Hindi spell like "आयुष" this so it works perfectly but the problem here is I generated the english version using the multilingual v2 as v2.5 is fluctuated in english letters and it does not support the CMU and IPA so thats the main problem I having here . can you tell how can we resolve this as I also tried with some phonetic english but still sound like an english man speaking not an indian but I have already seleted en-Indian while generating PVC clone voice
2 likes • 3d
@Jaskaran Saini But it still sounds different on the pitch of the sound as I generated the whole script with multilingual v2 and the only name was generated with turbo v2.5 is still sounds different as I choose the same settings
HEYGEN VIDEO IMPROVEMENT
Hye Guys I want to improve the quality of the video through heygen . Quality means the clarity and picturization of the video not the resolution . As currently I just uplaod the audio generated from the elevenlabs and use my Digital twin trained on my original video, and it generate a video thats it but how can I enhance the video or what other possibilities around heygen video generation
HEYGEN LIP SYNC
Hey I am tried to train the digital twin under 200mb from IPHONE using the 1080P at 30 FPS the video file has been under the HEYGEN cap . But after the training the digital twin it make default Audio and lip movements different from what I have uploaded SO when trying to use the audio from the another platform like ELEVENLABS , MINIMAX and uploaded the audio in HEYGEN but when the video generated the Lip sync is getting very off How can I resolve this issue . or what will be the best approach for making the video Lip sync perfect
HEYGEN UPLOAD ISSUE
the issue is I recorded my self from I phone and the file size has became 1 GB for 3 minutes of recording but the HEYGEN only takes 200MB max data at once and there is no option of multiple videos to Train DIGITAL TWIN Is there any way possible to get that video which is original of 1GB can be upload and can get trained
3 likes • 8d
@Muhammad Khan thanks man . it is a great help
3 likes • 8d
@M J it is a great tip the ffmpeg one I will definitely try it
HEYGEN VIDEO QUALITY
Hey guys I want to know using AVATAR V how can get the best quality video . Is it we have to get good quality digital twin or what else As i tried with 4k output but still it getting not good quality video
1-10 of 10
Navneet Singh
4
39 points to level up
@navneet-singh-7862
Developer and content creator exploring the future of AI-driven video

Online now
Joined Nov 7, 2025
Powered by