Visit our voice bank, where you will find nearly 120 professional voice artists. AI voices are algorithms and cannot match the abilities and skills of real voice artists, with whom we can produce even the most demanding recordings.

To generate audio in another language, simply type or paste text in that language.
Chinese, Korean, Dutch, Turkish, Swedish, Indonesian, Filipino, Japanese, Ukrainian, Greek, Czech, Finnish, Romanian, Russian, Danish, Bulgarian, Malay, Slovak, Croatian, Classical Arabic, Tamil, English, Polish, German, Spanish, French, Italian, Hindi and Portuguese.

Yes! Carefully edit your text to make the generated audio sound its best.

Punctuation is very important. The algorithm interprets punctuation marks to make the voice's intonation as natural as possible.

It is best to write numbers as words — for example, “nineteen-year-old” rather than “19-year-old”. Consider writing difficult names or abbreviations phonetically.

Of course. Please use our contact form and tell us what you need.

FOR TEXT TO SPEECH:

1 token = 1 character (including special characters and spaces)

Example: generating speech from 250 characters of text deducts 250 tokens from your account.

FOR SPEECH TO SPEECH:

1 second of audio = 20 tokens
1 minute of audio = 1,200 tokens

Example: generating speech from a 25-second audio file deducts 500 tokens from your account.

FOR VOICE ISOLATOR:

1 second of audio = 20 tokens
1 minute of audio = 1,200 tokens

Example: using Voice Isolator on a 25-second audio file deducts 500 tokens from your account.

Voice Isolator removes background noise from audio recordings to produce clean, studio-quality sound. It is particularly useful for recordings made in noisy environments or containing unwanted ambient sounds. Its benefits include cleaning up recordings and supporting various audio file formats.

Shorter texts generate faster and, if an error occurs, do not cost the user an excessive number of tokens. 3,600 characters including spaces equal two standard A4 manuscript pages, usually typed in 13-point Times with double spacing. If you need to combine several generated audio files and do not know how to do it, get in touch. We can also help with other tasks, such as adding music to a voice over or editing the audio to your requirements.

Yes. The person who creates the generated audio file becomes its owner. Remember that the voice is generated by AI and is not the voice of a real person.

No. Advanced AI models generate realistic-sounding synthetic voices designed to imitate different styles and accents for a range of uses and languages.

There is no direct control for the emotional content of the generated audio, but you can adjust voice settings to obtain different performances. Factors such as capitalisation and grammar may affect the output. Each voice also includes suggested uses, such as audiobooks, narration, animation, video games, news or meditation.

Mispronunciation can have several causes. The most common is a misspelt word. The AI does not try to correct spelling and attempts to read words exactly as written. It is therefore important to proofread and finalise your text before clicking GENERATE AUDIO.
Sometimes the AI may mispronounce words or produce an unexpected accent. This can happen for various reasons and usually depends heavily on the voice and language.
The text determines the language, while the voice determines the accent. If you write in a language that shares many words with, or is closely related to, another language, the AI may struggle with pronunciation or switch between accents.
In some circumstances, the AI may mispronounce correctly spelt words, even in English. This appears to depend largely on the voice and text used and should be very rare.

Znaki nieprzypominające tekstu oraz interpunkcja takie jak {, }, , [, ] zazwyczaj skutkują niską jakością mowy generowanej przez model.

Supported formats for the input file, which supplies the content and emotional delivery for the generated speech, include:
MP3 at a sample rate of 44.1 kHz and 64 kbps.
MP3 at a sample rate of 44.1 kHz and 96 kbps.
MP3 at a sample rate of 44.1 kHz and 128 kbps.
MP3 at a sample rate of 44.1 kHz and 192 kbps.
PCM (S16LE) at a sample rate of 16 kHz.
PCM (S16LE) at a sample rate of 22.05 kHz.
PCM (S16LE) at a sample rate of 24 kHz.

Please use our contact form and we will try to resolve the problem.

Of course. After you place an order in our shop, a VAT invoice is generated automatically and sent to the email address provided. It will also be available later in your account after you log in.