When cloning a voice, it’s important to consider what the AI has been trained on: which languages and what type of dataset. In this case, the following are available Mult ...
With the introduction of the newer models, we also added a style exaggeration setting. This setting attempts to amplify the style of the original speaker. It does consume additiona ...
Try changing your voice settings; you'll find them in the "Voice Settings" tab. Each attempt to generate a voice will bring a different result (especially visible at low stability) ...
We only deliver audio in the MP3 format 44.1kHz/16bit MP3 in 96kbps
The similarity slider dictates how closely the AI should adhere to the original voice when attempting to replicate it. If the original audio is of poor quality and the similarity s ...
Like we are proud to say always using our platform is easy for everyone ! Here is a quick tutorial about how to create voice -
Using the pause feature creates an exact and natural pause in the speech. The AI can handle breaks of up to 3 seconds in length. You can embed the pause where you want the break t ...
Music brings life to your content creation . Here is a quick tutorial about how to add music on Voice Air -
We know that the voices tend to degrade or start whispering during longer audio generations, and our team is working hard to develop the technology to improve this. This issue is m ...
Audio outputs and their corresponding text prompts. In this part, we’re highlighting what the text to speech AI can do, particularly in expressing variety of emotions. Keep ...
Multilingual v2 This model has good stability, great language diversity, and fantastic accuracy in cloning voices and accents. Its speed is rather remarkable considering its si ...
A guide on using stability, similarity sliders for tailored voice performances in Voice Air. Learn how to strike a balance between emotive and consistent audio outputs. Our users ...
Numbers, acronyms, and foreign words sometimes default to English when prompted in a different language. For instance, the number "11" or the word "radio", typed in a Spanish promp ...
Based on varying user feedback and test results, it’s been theorised that using a singular long sample for voice cloning has brought more success for some, compared to using ...
We do not have any integrated solution to force a certain pronunciation. However, we are developing a proper solution and the tools to force and fine-tune pronunciations. But, at t ...
All created voices are expected to maintain most of their original speech characteristics across all languages, including their original accent.
The stability slider determines how stable the voice is and the randomness between each generation. Lowering this slider introduces a broader emotional range for the voice. As men ...
There are a few ways to introduce a pause or break and influence the rhythm and cadence of the speaker. The most consistent way is programmatically using the syntax < break time ...
To create highly engaging content a video is a must. Here we have provided a quick tutorial of how to add video content.
A guide on how to generate voiceovers using your voice in Voice Air. Now that you have your voice, it’s time to generate some voiceovers! To convert text to speech, hover ...
No textual-like characters and punctuation such as {,},<,>,[,] will usually result in low-quality speech generated by the model.
We are working on features that will allow for speed optimization.
Unfortunately, we don’t have any such list of symbols. While the model responds to changes in pronunciation, there isn’t a predefined list of symbols that could be ...
We plan on introducing features that allow emotions such as laughter later in the year.
Effective techniques to guide Voice Air AI in adding pauses, conveying emotions, and pacing the speech.
These options are inconsistent and might not always work. We recommend using the syntax above for consistency. One trick that seems to provide the most consistence output - sans t ...
The AI has been trained on a vast amount of audio. The type of audio varies, but the mostprominent is audiobooks. This is the context it understands the best, and it provides t ...
When the voice drops in volume, whispers, or distorts, this is most likely a stability issue. How prevalent this is also dependent on the voice used and how wide the dynamic range ...
Here you will find a quick guide on how to export your content and save to your local device.
This is another setting that was introduced in the new models. The setting itself is quite self- explanatory – it boosts the similarity to the original speaker. However, usin ...
You have up to a maximum of 15,000 characters per production, and you can add multiple voices and voice segments with a total of 1500 characters per segment. The reason why there ...
The user’s experience is very important to us and here you will find a walkthrough of Voice Air.
You can use the voice and content of others with their consent. You need to get their permission before using their materials on voice cloning technology. Contact the creator (or ...
Today, intellectual property and related rights apply to almost any content we make. Most rights do not need to be registered to apply; they arise when new content is created. Righ ...
“Crediting your sources” means naming the person who created the materials you have used to generate your voice clone. You credit someone by attributing their name to ...
You are sometimes allowed to use someone else’s voice or content (like text or sound recordings) without their permission. This will be the case in limited circumstances incl ...
Not yet but we will add it very soon.
It's not available within Voice Air right now, but we will have this in the near future.
Audio is generated in several seconds. The system then undergoes post-production to achieve the quality you desire. The shorter the script, the faster your audio will generate.
No, we don't have that feature.
Yes, it is. ElevenLabs provides this feature, which is one of the best Instant Voice Clone features available.
You can create multiple folders for multiple projects.
Yes you can add multiple images on timeline editing suite . Here is how you will be able to do it -
Yes, you sure can.
Yes, you have many options to be able to edit your projects, take a look at one of our many tutorials within our Knowledge Base.
You have the option to preview your generated audio, but please note that every time you preview, this will deduct characters from your allocated limits.
All the voices are premium; we don't grade them within the voice library.
In most cases, yes. It may mispronounce something challenging to say for AI. We would suggest spelling numbers, for example, twelve rather than 12.
We will release this during this quarter.
Please contact us if you do not receive an automated invoice from our payment provider, please check your spam folder as well. In turn, you can contact us at support@voiceair.ai to ...
Air Projects offers users the ability to create long-form audio content.
The limitation per project is 15,000 characters. You have the option in Air Projects to not be capped with character limits, but please note this is solely for audio genration.
Currently any projects you create on either the web or mobile applications, will not be available to edit. However, this feature will be available in late Q2 and we will inform all ...
You can mark your favourite voices within both mobile and web versions of Voice Air.
yes, we do, and you can find it https://roadmap.voiceair.ai/
We want to give users the opportunity to keep their projects for as long as possible, however we have to be able to sustain such a feature. So, currently we are offering unlimited ...
Follow this link: https://app.voiceair.ai/login
Whenever you edit and regenerate words, an API call is sent to ElevenLabs, and this is deducted from your monthly character limit. We are working on a solution where the only chara ...
Air Projects is for long-form audio generation, such as audiobooks. You can upload a file, and Air Projects will help you create longer audio files with no character limits.
Follow this link: https://app.voiceair.ai/my_account
Yes, you can on both our Air Projects and the Voice Air content creation platforms.
Here is the tutorial or walkthrough of our v2 web application of voice air
Yes, you can.
The Voice Air subscription plan is based on character usage . Each time a user generates a voice, previews it, or adds it to the timeline, characters are deducted from your subscr ...
