Unlimited Seedance, Kling, Wan and Seedream 5.0, now on KreatorFlow · available now · Fair use

See passes
KREATORFLOW
Log inSign up

Official BytePlus partnerBytePlus, a ByteDance company

AI text to speech

AI text to speech with lifelike voices in 14 languages

Turn any script into natural speech. Paste up to 5,000 characters, choose one of 45 voices, set the speed, pitch and emotion, or write a two-speaker dialogue, then play and download the clip.

  • 5,000 characters per clip
  • 14 languages
  • Two-speaker dialogue
  • 2 credits per 1,000 characters
Open Text to SpeechBrowse the voice library

Last updated

On this page
  1. From script to speech in three steps
  2. Two-speaker dialogue mode
  3. Voices to start with
  4. Delivery controls
  5. Pricing
  6. Text to speech by language
  7. Text to speech questions
  8. Keep exploring

From script to speech in three steps

  1. 1

    Paste your text

    Up to 5,000 characters per clip, about the length of a long article section or a short video script.

  2. 2

    Choose and tune a voice

    Pick a voice, then set the speed from 0.5x to 2x, the pitch, the volume and, on emotion-capable voices, the emotion.

  3. 3

    Generate

    The clip plays in the browser and is saved to your audio history, ready to download.

Two-speaker dialogue mode

Switch to Two speakers mode to write a conversation. Pick a voice for Speaker A and one for Speaker B, write the turns, and the studio generates each line in the right voice. Play all plays the whole dialogue in order, which is handy for podcast intros, interviews, ads with two characters and language-learning scenes.

Voices to start with

One voice per language, under its real studio name. All 45 voices are in the Voice Library.

Delivery controls

Speed

0.5x to 2x, for slow explainers or fast social cuts.

Pitch

A lower or higher tone for the same voice, so one voice can fit different characters.

Emotion

8 emotions with an intensity setting on emotion-capable voices.

Volume

Set the loudness so the voice sits right in your edit.

Pricing

Text to Speech costs 2 credits per 1,000 characters, with a minimum of 2 credits per clip: a 800-character script costs 2 credits and a full 5,000-character script costs 10 credits. The studio shows the cost before you generate, and failed clips are refunded automatically.

Text to speech by language

One page per language with at least two preset voices: its voices, tips and common questions. Also in Text to Speech, with one voice each: Italian (Matteo), Vietnamese (Mai) and Thai (Napha).

Text to speech questions

How long can my text be?

Up to 5,000 characters per clip. For longer scripts, split them into parts and generate each one.

How much does text to speech cost?

Text to Speech costs 2 credits per 1,000 characters, with a minimum of 2 credits per clip: a 800-character script costs 2 credits and a full 5,000-character script costs 10 credits. The studio shows the cost before you generate, and failed clips are refunded automatically.

Which languages are supported?

14 languages with preset voices: English, Mandarin, Japanese, Spanish, Portuguese, Indonesian, French, German, Korean, Arabic, Russian, Italian, Vietnamese, Thai. For more languages and accents, Audio Generation speaks 24 languages from a written prompt.

Can two voices talk to each other?

Yes. Two-speaker mode gives Speaker A and Speaker B their own voices, generates each line and plays the dialogue back in order.

Can I download the result?

Yes. Every clip can be downloaded, and it stays in your audio history.

Which platform does the audio studio run on?

Built on BytePlus, a ByteDance company. KreatorFlow is an official partner of BytePlus, a ByteDance company; the audio studio and its credit prices are KreatorFlow's own.

Turn your script into speech

Paste your text, pick one of 45 voices and generate. 2 credits per 1,000 characters.

Open Text to SpeechBrowse the voice library

Keep exploring