Q: Why can’t we preview text before generating content?
All other text to speech programs I have used allow me to preview text before I generate anything. Are you adding this feature? My purchase is based on this answer.
A: Great question! A text preview feature isn’t available yet, but it’s on our list since we know how valuable it is. For now, you’ll always see the exact credit cost before generating, so there are no surprises. We’d love it if you could upvote this on our roadmap https://voispark.canny.io/general-feedback The more requests, the sooner we can ship it. Thanks for the feedback and for helping us...
May I ask which tool you’re using that allows text preview? As far as I know, none of the leading voice AI tools currently support this feature. But if you’ve seen it working elsewhere, I’d be very happy to explore it further. Thanks!
Thanks for the info, Paul197. Our team will look into it.
Q: From a no-native English speaker to a native English speaker.
Hello Team,
I would like to use this app for generating my podcast. English is my second language, and obviously, a native English speaker can pick up an accent. How can I use VoiSpark to record my podcast with my voice, but in perfect American English? How should I do it?
A: That's a really great question! Voice cloning does capture accents.
1/ When you do the recording, try using sentences where you have less of an accent. This way, you feed the model voices with less accent.
2/ Minimax captures accents much better than Catesia and Fish Audio. So, I suggest that after you record your voice, you choose either Catesia or Fish Audio to clone your voice.
Also, here’s a trick you can try - When you record, say something in your native language. However, when you clone it, make sure the text is in English. This way, the generated voice will be your voice but with less of an accent.
Q: how many hours/minutes/words does 120k cover to convert to
how many hours/minutes/words does 120k cover to convert to
Cloning a voice with the Minimax model has a one-time cost of 100K credits since it’s a very advanced option, while other models like Fish Audio or Cartesia are much cheaper for the first clone. After that, — usually about 1–4 credits per character (roughly 1,000 characters ≈ 1 minute of audio). And no surprises: before you hit generate, the system always shows the...
VoiSpark doesn’t include voices from ElevenLabs (like “Arabella”), and there’s no Arabella voice ID available here — they’re completely separate platforms.
However, on VoiSpark, you can:
Create your own custom voice by cloning (so it can sound similar to your preferred style), and Generate Korean-language audio using any supported voice model.
From 2024 to 2025, Minimax audio price almost dropped to half of its initial price. Credit to audio duration ratio remains unchanged. This seems to be the trend. Will VoiSpark give more credits in the future per month?
About your question: providing more monthly credits is something the team is actively evaluating. If you don’t mind, would you share what you’d need those extra credits for (e.g. hours of podcast, many voice clones, long-form content)? That helps us understand what levels will be most helpful.
Thanks so much for paying attention and giving us feedback — it’s this kind of...
I would like to have extra credits for longer audio duration if Minimax or other provider pricing drops in the future. I got a lot of content that I want to generate to audio. Will VoiSpark offer more MiniMax credits per month for existing LTD customers if MiniMax reduces pricing significantly?
Q: Why can’t we preview text before generating content?
All other text to speech programs I have used allow me to preview text before I generate anything. Are you adding this feature? My purchase is based on this answer.
Skylar_VoiSpark
Sep 28, 2025A: Great question! A text preview feature isn’t available yet, but it’s on our list since we know how valuable it is. For now, you’ll always see the exact credit cost before generating, so there are no surprises.
We’d love it if you could upvote this on our roadmap
https://voispark.canny.io/general-feedback
The more requests, the sooner we can ship it. Thanks for the feedback and for helping us...
Share VoiSpark
May I ask which tool you’re using that allows text preview? As far as I know, none of the leading voice AI tools currently support this feature. But if you’ve seen it working elsewhere, I’d be very happy to explore it further. Thanks!
I am able to use the preview feature using the following Text To Speech Programs...
Micmonster, Odio, Lazybird, Speechactors, and Unmixr.
I am interested in this Text to Speech program also because of their voices offered, but would only be interested if the preview option shows up.
Thanks for the info, Paul197. Our team will look into it.
Q: From a no-native English speaker to a native English speaker.
Hello Team,
I would like to use this app for generating my podcast. English is my second language, and obviously, a native English speaker can pick up an accent. How can I use VoiSpark to record my podcast with my voice, but in perfect American English? How should I do it?
Bingchen_VoiSpark
Sep 25, 2025A: That's a really great question! Voice cloning does capture accents.
1/ When you do the recording, try using sentences where you have less of an accent. This way, you feed the model voices with less accent.
2/ Minimax captures accents much better than Catesia and Fish Audio. So, I suggest that after you record your voice, you choose either Catesia or Fish Audio to clone your voice.
Share VoiSpark
Also, here’s a trick you can try - When you record, say something in your native language. However, when you clone it, make sure the text is in English. This way, the generated voice will be your voice but with less of an accent.
Q: how many hours/minutes/words does 120k cover to convert to
how many hours/minutes/words does 120k cover to convert to
Skylar_VoiSpark
Sep 22, 2025A: Hi, happy to clarify here!
Cloning a voice with the Minimax model has a one-time cost of 100K credits since it’s a very advanced option, while other models like Fish Audio or Cartesia are much cheaper for the first clone. After that, — usually about 1–4 credits per character (roughly 1,000 characters ≈ 1 minute of audio). And no surprises: before you hit generate, the system always shows the...
Share VoiSpark
Q: Can I use it for Korean accents? Arabella voice ID from Elevenlabs?
Hi, does it have Arabella from eleven labs and can I use it for Korean language commentary?
Skylar_VoiSpark
Sep 17, 2025A: Thanks for checking 💛
VoiSpark doesn’t include voices from ElevenLabs (like “Arabella”), and there’s no Arabella voice ID available here — they’re completely separate platforms.
However, on VoiSpark, you can:
Create your own custom voice by cloning (so it can sound similar to your preferred style), and
Generate Korean-language audio using any supported voice model.
Share VoiSpark
Q: Will VoiSpark give more credits in the future
From 2024 to 2025, Minimax audio price almost dropped to half of its initial price.
Credit to audio duration ratio remains unchanged. This seems to be the trend. Will VoiSpark give more credits in the future per month?
Skylar_VoiSpark
Sep 17, 2025A: Good observation!
About your question: providing more monthly credits is something the team is actively evaluating. If you don’t mind, would you share what you’d need those extra credits for (e.g. hours of podcast, many voice clones, long-form content)? That helps us understand what levels will be most helpful.
Thanks so much for paying attention and giving us feedback — it’s this kind of...
Share VoiSpark
Verified purchaser
I would like to have extra credits for longer audio duration if Minimax or other provider pricing drops in the future. I got a lot of content that I want to generate to audio. Will VoiSpark offer more MiniMax credits per month for existing LTD customers if MiniMax reduces pricing significantly?