![](avatars/54274.jpg)
- Time
- Post link
This method could be useful for achieving better intonation, as it changes the voice of an existing recording: https://www.youtube.com/watch?v=jQBQfJqacLA
Hmm, that voice wasn’t quite as convincing.
This method could be useful for achieving better intonation, as it changes the voice of an existing recording: https://www.youtube.com/watch?v=jQBQfJqacLA
That’s moreso for music covers I thought?
The truth of the matter concerning our current voice clone is that Adam Driver is reading an audio book with a higher pitched, cheerier voice. Meanwhile, Kylo speaks with a very dark authority in these scenes. Krlozdac and I tried to lower the pitch on the voice outputs but there’s only so much that can do.
I think the previous voice sounded better aswell
“You will find that many of the truths we cling to depend greatly on our own point of view” — Obi-Wan Kenobi
I’ll let krlozdac handle the new lines we want then since he seems to be getting better outputs than me.
Ideally, we could throw in some mask less Kylo audio from Lego TFA to help balance out the results, but it seems Octorox’s drive no longer has any of the audio from that game.
Voice conversion can definitely be used for dialog/talking too. It’s not exclusively for music/vocals. It’s what Disney did for Luke and Vader in Mando/BOBF and Kenobi. The key is getting a VA that can get close enough to the intended voice and then you use the voice conversion to get it the rest of the way there.
This is the last I’ll be able to generate probably till monday.
Here’s a stab at it: https://drive.google.com/file/d/17kzfyuXIxmZvU1qfDMKtwzV9Wv6cD6N-/view?usp=sharing
And the line in isolation: https://drive.google.com/file/d/13e05pAmn4e0G1V9mKIaCyCAp0DIgVPhB/view?usp=sharing
I think you pitched it a little too harshly. It’s starting to sound like he’s got his mask on.
I think you pitched it a little too harshly. It’s starting to sound like he’s got his mask on.
Got it. Will adjust in next render.
Could you also try having there be a slight space between the two clauses?
“You’re a ghost. In a rotting clone.” With a derisive tone.
Use the following prompt to get it to speak slower krlozdac:
“You’re a ghost… In a rotting clone…”
The periods help a lot.
Here are two test I had time to put together: https://drive.google.com/file/d/1skwWcHS3STJdEGOoNNSTji1qBlDo2wwW/view?usp=sharing
Whatever you did here sounds nearly perfect and I can’t seem to replicate it on my end. Your two other recent tests sound robotic so if you’re doing the same thing for everything I’m not sure what happened.
EDIT: FINALLY replicated it with the new line - https://youtu.be/4OoYAj4iFcM
Here are two test I had time to put together: https://drive.google.com/file/d/1skwWcHS3STJdEGOoNNSTji1qBlDo2wwW/view?usp=sharing
Whatever you did here sounds nearly perfect and I can’t seem to replicate it on my end. Your two other recent tests sound robotic so if you’re doing the same thing for everything I’m not sure what happened.
EDIT: FINALLY replicated it with the new line - https://youtu.be/4OoYAj4iFcM
I have been using the same methods throughout but as you know this whole thing is a crapshoot.
That one you got is pretty great. The hardest thing for me has been to get the voice not to sound too animated given that in the source of the audio he’s giving a very lively reading.
EDIT: FINALLY replicated it with the new line - https://youtu.be/4OoYAj4iFcM
This is the best one ive seen so far! I’m no audio editor, but it perhaps could have slightlyyyyyy a bit more of a deeper tone, not sure if this can be done with sperate software or not though.
“You will find that many of the truths we cling to depend greatly on our own point of view” — Obi-Wan Kenobi
I can fix that. The original line was already a bit deep, so I didn’t apply as significant of a pitch change to it before putting it into the video. I still have the original so I’m going to experiment with EQ and a more impactful pitch change.
EDIT: Here is a -5 pitch change instead of -3 (Audacity) plus some EQ: https://youtu.be/IPEDsdQrjlc
I can fix that. The original line was already a bit deep, so I didn’t apply as significant of a pitch change to it before putting it into the video. I still have the original so I’m going to experiment with EQ and a more impactful pitch change.
EDIT: Here is a -5 pitch change instead of -3 (Audacity) plus some EQ: https://youtu.be/IPEDsdQrjlc
That’s pretty spot on if you ask me.
Give it a bit of reverb and drop the volume a tad and it may be seamless.
You probably don’t recognize me because of the red arm.
Episode 9 Rewrite, The Starlight Project (Released!) and ANH Technicolor Project (Released!)
Give it a bit of reverb and drop the volume a tad and it may be seamless.
👌
Could the original delivery of “What could you give me” be sort of flattened a bit so it does not stick out as much more dynamic?
Not unless you want it to no longer have the gap space between “you” and “give me”. It would be a very quick reading more than likely.
I’m not skilled at applying reverb but here it is with quieter volume and a very slight vocal reverb: https://youtu.be/8NFKKmt56yU
Here is the file with only pitch and eq changes so somebody else can tinker with the reverb and volume: https://drive.google.com/file/d/1SA_mjRJS5yGCpETffTrWumPEf5P34MW1/view?usp=sharing
Not unless you want it to no longer have the gap space between “you” and “give me”. It would be a very quick reading more than likely.
I don’t mean recreating that line with AI, just flattening the existing line from the movie so that it sticks out less against the AI line that is right before it.
Ah… I’m not sure what feature might do that in audacity?
I can play around with that and see. Might give it just slight ‘telephone’ effect and see if it helps the new AI line fit in. But I downloaded your latest clip and think it’ll probably be our best bet for this idea.
Well, here is the line: https://drive.google.com/file/d/1DlAeu7w-_XekhE4uj-zLkWNyiXimKWJW/view?usp=share_link
Can anyone translate for subtitle purposes?