Text-to-Speech Online

Paste text, pick a preset voice, generate an MP3, adjust playback speed, and download in one workspace.

Text bubble and microphone icons linked by a glowing arc above a text-to-speech label.

Features

  • Preset OpenAI voices (Alloy, Echo, Fable, Onyx, Nova, Shimmer) ready to use inside Sondeas.
  • Built-in player with playback speeds from 0.5x to 5x before you export.
  • MP3 files are stored with each encrypted note so you can download or revisit them later.
  • Pair with transcription and translation because every feature uses the same credits.

How to use

  1. 1

    Paste or type your text.

  2. 2

    Select one of the preset voices (Alloy, Echo, Fable, Onyx, Nova, or Shimmer).

  3. 3

    Click Generate to create speech and listen inside the built-in player.

  4. 4

    Download the MP3 or keep it stored with your note.

FAQ

Which voices can I use?
Alloy, Echo, Fable, Onyx, Nova, and Shimmer are available — the same preset voices wired to the OpenAI tts-1 API.
Can I change playback speed before exporting?
Yes. The built-in audio player supports playback from 0.5x to 5x so you can review audio before downloading the MP3.
Are credits shared with transcription?
Yes. One balance covers transcription, translation, and TTS.

Voice preview scripts

Alloy

Neutral narrator with steady pacing

Alloy keeps your status updates calm, clear, and easy to share.

Nova

Bright, energetic read

Nova adds a friendly lift to onboarding tips and quick customer success recaps.

Onyx

Deeper, confident voice

Onyx is ideal for executive summaries or weekly wrap-ups that need authority.

Paste these lines into the editor and click Generate to hear each voice inside the player before downloading.