Write the words, choose a voice, and download the read. Useful for a spoken intro to a track, a radio-style ad read for a release, or narration over a lyric video.
From a typed script to a spoken audio file in three steps.
A voiceover is a spoken track you lay over something else. For a release, that is the radio-style read on a pre-save ad, the spoken intro before the first verse, or the narration on a lyric video. Write the words the way you would say them, with punctuation where you want a pause, and try the same line on two voices before you pick one.
Yes, for a short script. Each started 1,000 characters, roughly 150 English words, costs 8 credits on Fast or 15 on Standard and Best. A new web account starts with 20 credits, enough for up to 2,000 characters on Fast or 1,000 on Standard or Best. On the free plan the balance tops back up to 10 credits each day you sign in, enough for another 1,000 characters on Fast. The price shows on the Generate button, and credits are refunded if a generation fails.
It reads a script. It does not clone your voice, sing, or change the voice in a recording you already have. A run takes up to 5,000 characters and uses one voice, so a dialogue between two speakers is made in separate runs and joined in an editor. There are no controls for speed, pitch, or emotion. The result is audio only; to dub a finished video into another language, use Video Translate.
Paste your script, select a voice, choose a tier, and generate. Download the audio when it finishes.
More than 70, including English, Spanish, Portuguese, French, German, Japanese, and Korean.
Commercial use follows your Solmi plan terms. Check the plan page for details.
A spoken recording generated from text. You type the script and pick a voice, and the tool returns an audio file you can place under a video, an ad, or a podcast segment.
Up to 5,000 characters per run. For a longer text, split it into parts, generate each with the same voice and tier, and join the files in an editor.