Frequently Asked Questions

What is Altered Studio?

Altered Studio is a next-generation audio editor that integrates multiple Voice AI technologies into a user-friendly application for the production of high-quality voice content for various industries, including podcasters, video game studios, and eLearning.

What is AI Voice changing software?

It is a software that changes the voice of a person. Traditional Voice Changers are based on Signal Processing, come across under various names, such as vocoders, and can modify the voice without been able to mimick a real person. Modern Voice Changers are based on Deep Learning and are able to mimic a real person in exchange of more computational resources. High-Quality Voice Changers are typically used by audio professionals in post-production in movies and games, while lower quality Voice Changers are used by consumers for fun. Altered Studio is the only post-production quality Voice Changer currently available.

What is an AI Voice Generator?

An AI voice generator is a software program that uses artificial intelligence and machine learning algorithms to synthesize or generate speech from written or spoken input. Altered Studio uses cutting edge Speech-To-Speech and emotive Text-To-Speech technology to create realistic-sounding human-like voices suitable for content Creators in many different industries.

What video and audio formats can be imported in Altered Studio?

Altered AI can be used for a wide range of voice content, including voiceovers, eLearning, podcasts, audiobooks, advertising, video game character voices, film and TV production, and more.

Is Altered Studio compatible with all operating systems?

Altered Studio is compatible with popular operating systems like Windows and macOS.

Is Altered Studio available on mobile?

No, Altered Studio is currently not supported on mobile devices.

Is there a free trial available for Altered Studio?

Yes, you can sign up for a free trial of our Creator plan of Altered Studio on our website. If you are interested in our Professional or Enterprise subscriptions please visit the pricing page. Also, note that we offer an online audio editor called voiceeditor.ai for free to our customers so that they can benefit from our tool even after their subscription.

Is Altered AI's Voice suitable for commercial use?

Yes, Altered Studio allows you to create professional sounding voice overs for commercial use in Video Games, Podcasts, Marketing, TV, Film and much more. Commercial licensing depends on the subscription plan.

Can Altered Studio be used with other audio or video editing software?

Yes, Altered Studio's output files can be easily imported and used with other audio or video editing software.

What audio quality does Altered Studio output?

Altered Studio outputs high-quality audio, offering professional-grade sound for various voice applications.

Does Altered AI have an API?

Yes, we offer an API for our Enterprise customers to easily integrate Altered Studio into other systems.

How does Altered Studio help reduce costs associated with voice-over production?

Altered Studio reduces Voice-Over production costs by offering the combination of Speech-To-Speech and Text-To-Speech AI Voices together with powerful audio editing features within the same tool. Creators use Altered Studio to bring Voice Over in-house. This allows them to quickly iterate on content and to reduce the dependence on expensive professional studios and cumbersome service workflows. The embedded audio editing features reduce the time spend on manual editing by eliminating the need to switch to other audio editors for various edits.

Does Altered offer educational discounts for students?

All of our plans include a licence for educational use in the price. Additional discounts are available for quarterly or annual plans. To find the right plan for your needs, please visit altered.ai/pricing.

How does Altered Studio calculate usage charges?

Usage charges vary for different features of Altered Studio. For Speech-To-Speech morphing, your usage is charged for the length of the first morph you do on a selection of audio. After that, any subsequent morphs on the same selection will not count towards your usage. For Text-To-Speech and text translation, Altered Studio uses Text Tokens, which are generally equivalent to 1 character of text. Higher quality third party voices (like the 'Google Studio' voices) consume a higher number of Text Tokens per character, this is displayed on the voice cards in the library.

Do I need a microphone to create voiceover with Altered Studio?

Yes, you should use a micphone for recording into Altered Studio. Any microphone will work, but of course a better mic will give you better recordings and therefore better synthesis results.

Do I need a professional recording environment to create a voice-over with Altered AI?

No, you just need a quite place with sound-dampening elements to avoid reverberation (think curtains and carpet, not hard, bare walls and floors). Make sure your recording is raw and clean with no background noise, fx or filters applied.

What is Speech-to-Text?

Speech-to-text is the process of converting spoken words into written text. Altered Studio analyzes your audio recordings, identifies spoken words and transcribes them into written text in our Transcription Editor.

What is the difference between a Professional voice and a Common voice in Altered Studio?

Professional voices in Altered Studio are high-quality, carefully curated voices ideal for professional projects, while Common voices offer a broader range of options for more casual use cases.

How many voices are available in Altered Studio's voice library?

The Voice Library contains up to 20 Professional and 800+ Common Voices for Speech-To-Speech Voice Morphing and as well as 20 Professional voices and hundreds of 3rd party Cloud TTS voices in a variety of languages. The available voices may vary depending on your subscription plan.

Do you have samples of your voices?

Yes, each voice card in the voice library has play buttons, so you can hear samples of the voices.

Can I use Altered Studio to create children's voices?

Yes, you can create children's voices using Rapid Voice Creation for short dialogue and ADR. If you want a full voice model of a child's voice, please contact Altered Studio to discuss voice modelling options.

What accents are available within Altered Studio?

Altered allows the Creator to morph their voice into a variety of accents and languages. Our Professional voices can either convert your accent into American or British in voice modes such as Performance, Flexi, and Clone, or maintain your accent in Timbre mode.

What languages does Altered Studio support?

Altered Studio supports a wide variety of languages in both Speech-To-Speech and Text-To-Speech.

What is emotive or 'speaking style' TTS?

Altered Studio's "Speaking Style" or emotive Text-To-Speech is a flexibile way of voicing a piece of dialogue. Altered Studio allows for 14 Speaking Styles for our Portfolio TTS Voices including whispering and shouting.

What is a Fast model in Altered Studio and how does it differ from other models?

A Fast model refers to a voice model that has been optimized for quicker processing and rendering times, allowing you to create AI-generated voice content more rapidly. For high-end post-production, we recommend using non fast models because they achieve the maximum quality possible.

What do the different model types do in Altered Studio?

Each model is designed for different use cases such as Timbre (cross-lingual) models, Performance (English) models, Flexi (English) models, Clone (English) models, and Narration (English) models. Each model type also has a "Fast" version which provides quicker, but lower fidelity synthesis. Learn more...

Can I combine TTS with STS?

Yes, Altered studio is an all-in-one AI voice creation tool that allows access to Speech-To-Speech Voice Morphing and Speaking Style Text-To-Speech. Both AI voice tools within Altered Studio can be used jointly to create a comprehensive AI voice solution for all Creators.

How do I use Altered Studio to create subtitles for my video content?

If you have a script, import it into Altered Studio, apply the Speech-to-Text effect with "Align Input Text" checked, to align your text to the audio, and then export the transcription as an SRT. If you don't have a script, use the Speech-to-Text effect to transcribe the audio, edit the transcription as needed, and export the transcription as an SRT.

Is the transcription service in Altered Studio accurate?

Altered Studio offers market leading transcription services from Google, and Microsoft Azure for high accuracy levels

Does Speech-To-Speech synthesis support emotional expressions and intonations?

Yes, the Target Prosody dial in the Morph effect allows the Creator to mold the final voiceover. Prosody is used to describe the melody and rhythmn of the voice, and the emotions that can be captured through voice, such as inflection, pace, pitch, intonation, duration and pause. The Target Prosody control allows the Creator to “direct” how much of the source voice performance they want to capture.

What is Speech-To-Speech Technology and how does it differ from Text-To-Speech?

Speech-To-Speech technology allows a Creator to change their voice to sound like another voice while maintaining their spoken performance. Whilst Text-To-Speech only generates what was written as a text input, with minimal ability to provide performance, Speech-To-Speech will match the spoken input performance to give a much more realistic output.

What creative dials are included in Speech-To-Speech Voice Morphing?

The Speech-To-Speech Voice Morphing effect has a variety of creative controls such as Target Prosody, Pitch Offset, Decreak, Age Shift, and Gender Shift. These features allow the Creator to control the final performance of the target speaker in Speech-To-Speech synthesis.

What is target prosody?

Target Prosody is the prosody of the Voice Actor (aka Target). The term Prosody is used to describe the melody and the rhythm of voice. It encapsulates the context and the emotion of the speech content and affects qualities such as inflection, pace, tonality/pitch, intonation, duration and pauses. The Prosody control in the Voice Morphing effect allows the Creator to blend the source voice performance with the Target Voice performance.

How can I improve the quality of my morph output in Altered Studio?

To improve the quality of your morph output, it is recommended to use clean, raw audio without any effects or filters applied. You should also ensure that the speaker is close to the microphone and avoid any background noise or room reverb. Additionally, you can experiment with different settings in the Morph panel, such as adjusting the Pitch Shift, Target Prosody, and Loudness Shift, or using the Power Envelope and Post-Processing settings to smooth out the sound and reduce artefacts and noise in the synthesis.

Can I change my voice with AI?

Yes, you can change your voice with AI using a Voice Changer software like Altered Studio that utilizes machine learning to modify your voice. Altered Studio's Speech-To-Speech synthesis technology gives you the power to change your voice, including age, gender and accent while maintaining your performance.

Can Altered AI do real-time processing?

No, Altered Studio is only for post production. It allows Creators to rapidly synthesize samples but not in a streaming manner because this would impact audio quality.

Can I do batch processing in Altered AI?

Our batch processing feature is available in the desktop version of Altered Studio, which is available on our Professional and Enterprise subscription plans.

What is Rapid Voice Cloning?

Rapid Voice Cloning is the process of creating an AI-generated voice model that closely resembles a specific individual's voice with only a few seconds of audio. This can be used for various applications, such as voiceovers, content creation, and more. The performance of Rapid Voice Cloning depends on the proximity of the Target Voice to Altered's training dataset and improves over time. For assured production quality results, please request a Custom Voice using this form.

How much voice data is required to create a custom AI voice?

It depends on your use-case. In many use-cases, it suffices to make a Rapid Voice Clone in Altered Studio by yourself with just 4-8 seconds of audio. For assured production-quality results, it is recommended to contact Altered to train a Custom Voice. To train a Custom Voice, you will need 60-90 minutes of clear and high-quality voice recordings. However, for many Target Voices, good results can be obtained from only 30 minutes of audio. The amount of training data required depends on the proximity of the Target Voice to Altered's dataset. Altered also offers special custom services with less that 30 min of audio, but at a higher cost.

Which languages are supported for Rapid Voice Cloning?

Rapid Voice Cloning can be used with any language because it uses the Timbre models that are language agnostic. However, since most of our training data is in English, the best results will be in languages that are acoustically similar to English.

What is the difference between Rapid Voice Cloning and a Custom Voice?

Rapid Voice Cloning is a quick process of creating a voice model in minutes, typically used for fast prototyping or testing. Custom Voice, on the other hand, involves creating a more refined and tailored AI-generated voice model for a specific brand or project, ensuring a unique and consistent vocal identity. Rapid Voice Cloning only requires a few seconds of training data and is available at all times to all users at no cost, while a full Custom Voice requires significantly more data.

What is a Speech-To-Speech or Text-To-Speech Custom Voice?

A Custom Voice is an AI-generated voice model tailored to a specific brand, project, or individual, providing a unique and consistent vocal identity for various applications like advertising, content creation, and more. A Custom Voice is trained by Altered for you and requires a larger amount of high quality data than Rapid Voice Cloning. Custom Voice models can be trained in both Speech-To-Speech and Text-To-Speech.

Can I use audio from a video to clone my voice?

Yes, you can use audio extracted from a video to clone your voice with Altered Studio. In fact, you can use Altered Studio to extract that audio with ease.

Is there a limit to how many Custom Voices I can create with Altered Studio?

Altered Studio Professional and Enterprise plans allow unlimited number of Custom Voices. Altered Studio Creator plan has a limit on the number of Custom Voices you can have in your library at a time.

Can I create custom AI voices for my brand or project?

Yes, with Altered Studio, you can create custom AI voices tailored to your brand or project, ensuring you a unique and consistent voice.

Can I use Altered Studio for Voice Cloning

Yes, you can make a Rapid Voice Clone in Altered Studio yourself with just 4-8 seconds of audio. If you require a highly nuanced Custom Voice model, please contact Altered to discuss this process.

What audio editing features are included in Altered Studio?

Altered Studio includes various voice AI tools and a range of audio effects, like voice morphing, text-to-speech, transcription, translation, noise reduction, integrated mixer, noise reduction tools and more. Altered Studio also includes audio normalization, equalization and various simple edits like cut, copy, past, crop, insert audio, and various other audio effects suitable for power users and audio professionals.

What makes Altered AI's audio editor stand out from other editing software?

Altered AI offers a full range of advanced Voice AI technology, a user-friendly interface, and an extensive range of features, such as voice morphing, Text-To-Speech, transcription, and translation, making it an ideal solution for creating high-quality audio content.

Does Altered AI support multi-track audio editing?

No, Altered AI does not currently support multi-track audio editing.

What is the Integrated Mixer in Altered Studio?

The Integrated Mixer in Altered Studio is a post processing feature that is available for all Effects and is displayed at the end of the Effect Properties. It allows you to control how the audio generated by the specific Effect blends into the existing audio with options such as Mix, Loudness (normalization), and Cross-Fade.

Does Altered Studio support audio editing effects?

Yes, Altered Studio offers a range of audio editing effects for filtering, normalisation, denoising, transformation and analysis of your audio. Altered also supports gain, pitch and volume adjustments, which can be used to enhance your voice recordings and create a more polished Voice content.

How do I use the History in Altered Studio to make changes to my audio?

The History Editing feature in Altered Studio allows you to track and revert to previous versions of your audio project, making it easy to experiment with different edits and changes. If you make a change in the history, this will flow through to the subsequent layers in your file, so you can go back and make edits to hear how they affect the end result.