AI Voiceover (Neural TTS)

The primary engine is Microsoft Edge neural TTS (edge-tts). If that engine cannot be reached, the system automatically falls back to the offline Piper engine. The result screen shows which engine was used.

You can enter at most 3,500 characters at a time, which is roughly a 3–4 minute voiceover. For longer texts you can split the text, voice the parts separately and join the pieces (with the Merge Audio Files tool).

The output is in MP3 format and can be played directly in the browser or downloaded with a branded file name.

Yes, the tool is currently offered free of charge; apart from the character limit there is no extra fee or membership requirement.

Yes. Before generating the voiceover you can adjust the speaking tempo with a speed slider from 0.75x to 1.25x.

The tool can be used for personal and commercial content drafts; however, for large-scale commercial releases (advertising, voice-over agency work, etc.) we recommend reviewing the licence terms of the edge-tts/Piper engines first.

No. The text is processed only temporarily while the voiceover is generated; when the process finishes, temporary files on the server are deleted automatically and no permanent record is kept.

Yes. You can upload the generated MP3 to the Merge Audio Files tool and combine it with other audio clips into a single file.