Text to speech as WAV
Generate a voice-over and keep it as WAV, a lossless format that audio and video editors accept without extra decoding.
Runs on our servers. Your text is sent there to make the result. Results are kept in your library for 7 days when you are signed in with library saving on, otherwise for 24 hours; uploads are deleted after 24 hours.
Preset for this page
- Format
- WAV
The tool below starts with these settings. Change any of them in the tool.
Your text is sent to our servers to make the speech. If you are signed in with library saving on, the result is kept 7 days; otherwise it is deleted after 24 hours.
0 of 10000 characters
How to
- Add your text. Paste the script into the text box and choose the language.
- Pick a voice and speed. Select a voice, listen to the sample and set the speed.
- Confirm WAV as the output. Check that the output format is WAV, so the file is not compressed, before you generate.
- Download and import. Download the file and drag it into your editing software.
When WAV is the right output
A compressed audio file such as MP3 discards some information to save space. That is fine for a final listen, but each time you edit and re-save a compressed file you lose a little more. WAV stores the audio without compression, so you can cut, change levels, add effects and export again without stacking up those small losses.
Choose WAV when the voice-over is going into an editor. A video editor, a digital audio workstation or a podcast production tool can import it directly, and its waveform shows exact sample positions for tight edits. It is also the format sound engineers prefer when you hand over stems, and many broadcast and e-learning specifications ask for it.
The cost is size. A WAV file is several times larger than an MP3 of the same length, so it is a poor choice for sending by email or uploading to a social app that recompresses the audio anyway. A practical workflow is to keep the WAV as your master, then export a compressed copy for sharing. This page sets the output format for you, so the voice, language and speed settings are the same as on the main text-to-speech tool. Only the container changes. Remember that synthetic audio may need a label when you publish it.