Turn any text or script into natural-sounding speech with Descript's text-to-speech voice generator. Choose from dozens of lifelike AI voices or create your own voice clones in minutes. It’s perfect for podcast intros, voiceovers, faceless videos, and more.
Experience the magic of text-to-speech. Fix mistakes in your audio recordings without trudging back into the recording studio. Descript’s Overdub uses AI to create a natural-sounding synthetic version of your voice that you can use in any audio or video you’re creating.
In a new Descript project, type out your script in the text editor or paste in the text you want to generate speech from. You can also use the Ask AI command in the Actions menu to write a script for you based on whatever criteria you want.
Press ‘@’ to assign a speaker to your script. You can enter a new speaker name and then Enable speech generation to start the process of cloning your voice. Or you can select Browse stock AI speakers to choose from a library of realistic stock voices, emotions, and styles.
The script will flash briefly to indicate your speech is being generated. Once that’s done, you can play back your newly generated voice audio, continue in an audio or video project, or export it by clicking Publish.
Turn text into sound with Descript by creating a high-quality text-to-speech model of your voice or selecting one from our ultra-realistic stock voices.
No. When creating an Overdub Voice, Descript users must positively affirm their identity and give Descript their express consent to train and generate a synthesized version of their voice.
Voice-training data that does not include this Voice ID cannot be used to create an Overdub Voice. In other words, unless you specifically consent to Overdub Voice creation, Descript will not create your Overdub Voice.
We verify this consent by authenticating the audio file uploaded against our training script to ensure that the voice recorded belongs to the person submitting it.
Overdub text-to-speech is free on all Descript accounts. Pro accounts get an unlimited Overdub vocabulary.
Yes. While you can create a custom Voice on Overdub with any subscription, Free and Creator plans are limited to a list of the 1,000 most common vocabulary words. Any words that are not on that list will be replaced with "jibber" or "jabber." To avoid this gibberish and gain access to the full vocabulary list, you can upgrade to the Pro subscription.
TTS voice quality relies on a number of factors, such as the quality of your microphone, background noise, and room surfaces. Check out our article on Overdub Voice Quality Tips for tips on how you can assure the best possible recording.
Turn any text or script into natural-sounding speech with Descript's text-to-speech voice generator. Choose from dozens of lifelike AI voices or create your own voice clones in minutes. It’s perfect for podcast intros, voiceovers, faceless videos, and more.
In a new Descript project, type out your script in the text editor or paste in the text you want to generate speech from. You can also use the Ask AI command in the Actions menu to write a script for you based on whatever criteria you want.
Press ‘@’ to assign a speaker to your script. You can enter a new speaker name and then Enable speech generation to start the process of cloning your voice. Or you can select Browse stock AI speakers to choose from a library of realistic stock voices, emotions, and styles.
The script will flash briefly to indicate your speech is being generated. Once that’s done, you can play back your newly generated voice audio, continue in an audio or video project, or export it by clicking Publish.
With Descript, you can generate and edit voice audio just by typing. Convert your text into speech, edit it, and export it in your preferred format—all in one place.
Descript's text-to-speech (TTS) capabilities use AI to generate incredibly realistic voices. Choose from a range of voice types—from corporate to conversational, masculine to feminine—to find the one that suits your project best.
Create and share your own AI voices for use in future projects, whether you want to take a breather and let AI handle that voiceover track, or fix or add to an existing recording without rerecording.
No, Descript does not allow others to clone your voice without your explicit consent. Your voice data is kept secure and confidential, and you can delete it at any time. We are committed to protecting our users' privacy and adhere to a strict code of ethics.
You can use Descript to generate up to 5 minutes of text-to-speech audio totally free. Then you can upgrade to unlock 120 minutes of TTS generation per month, and a slew of other AI features, starting at $24/month.
Our free plan limits you to 5 minutes of text-to-speech audio generation, and 5 uses of Regenerate and Overdub to repair or change spoken audio. On our paid plans, you get monthly usage limits starting at $12/month for 30 text-to-speech minutes and 10 Regenerate and Overdub uses, among other perks.
You can improve the quality of your text-to-speech voice clone by recording in a quiet environment, speaking clearly and naturally as you read the sample script, using a high-quality microphone, and following Descript's recording guidelines in the prompt.
