Your first generation

Five steps

1. Open Speech Studio — it lands you on the Text to Speech page.
2. Paste or type some text in the main editor (up to 250,000 characters on Free).
3. Click the Voice dropdown at the top and pick any voice. For a great first impression, try en-US-Ava Multilingual or en-US-Brian:DragonHDLatestNeural.
4. (Optional) Adjust Rate, Pitch, or Volume below the editor. Or pick a Style (cheerful, serious, customerservice).
5. Click Convert Text to Speech. The audio generates in a few seconds and plays back in the player at the top.

Export

Once audio generates, the player shows Save-as-MP3 and Copy-to-clipboard buttons. MP3 is the usual pick for sharing; WAV is also available (higher quality).

What to do next

• Try different voices — 603+ options in the voice picker
• Use SSML for fine control (pauses, emphasis, multi-voice) — see SSML editor
• Import a PDF or DOC (Pro) — see file imports
• Set up your own Azure key for unlimited use — see Azure setup