Available now

ElevenLabs TTS v3: text to speech

By ElevenLabs

ElevenLabs' Eleven v3 reads your text aloud in the voice you name, up to 5000 characters per run, with word timestamps when you need them.

Model ID
Maker
ElevenLabs

Input

Fields marked * are required. Review the price before generating.

The text to convert to speech

Example. Edit it or write your own.

Additional settings

The voice to use for speech generation

Use a suggested voice or enter an exact voice ID.

Voice stability (0-1)

Whether to return timestamps for each word in the generated speech

Language code (ISO 639-1) used to enforce a language for the model.

Price$0.17 / run

You sign up first. Your settings are kept.

About this model

Overview

Paste a script and Eleven v3 turns it into speech. Name a voice or keep the default, and set stability: lower values give a more varied, expressive read, higher ones a steadier tone.

You can fix the language with a two-letter code when the text could be read as more than one, and choose whether numbers and abbreviations are spelled out for you.

What you can build

  • Voice-overs for product videos and ads
  • Narration for lessons, guides and audiobooks
  • Spoken lines for characters in a game or animation
  • Subtitles timed from word timestamps

Prompting tips

  • Write numbers, dates and abbreviations the way they should be spoken, or leave text normalization on.
  • Lower stability for a lively, acted read; raise it for an even tone across a long script.
  • Steer pauses with punctuation: commas for short breaks, full stops and new sentences for longer ones.

What to check

Listen for correct names, numbers and pauses. Compare the transcript with the audio before publishing or generating subtitles.

Inputs

  • Text (required): The text to convert to speech.
  • Voice (optional): The voice to use for speech generation.
  • Stability (optional): Voice stability (0-1).
  • Timestamps (optional): Whether to return timestamps for each word in the generated speech.
  • Language Code (optional): Language code (ISO 639-1) used to enforce a language for the model.
  • Apply Text Normalization (optional): This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Options: auto, on, off.

Output and limits

  • Sung or spoken words can come out unclear or differ from your text.
  • Exact length, tempo and key are not guaranteed; listen to the whole result before you use it.
  • Prompts that name real artists or protected songs can be refused.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to · 1,000 characters: $0.17 / run