Text to WAV
Generate speech from text and download it as an uncompressed WAV file ready for editing.
If the voice you generate is going into something else, such as a video timeline, a podcast episode with music, an e-learning module or a game prototype, the file format matters more than it seems. WAV is uncompressed, so it keeps all of the generated audio and survives editing and re-exporting without piling up quality loss. This page explains when WAV is worth the larger file, how to bring it into an editor cleanly, and when you are better off downloading an MP3.
Open the tool → Opens the tool with WAV selected as the download format.- Free, no limitNo account, no character cap, no watermark.
- Nothing is uploadedYour text is turned into speech on your device and never reaches a server.
- Works offlineAfter the first use the tool keeps working with no connection.
- Audio and subtitlesDownload MP3, WAV, or an SRT file timed to the speech.
Why editors prefer WAV
An MP3 discards some audio information to make the file small. That is fine for listening, but when you edit an MP3 and export again to a compressed format, the encoder compresses audio that was already compressed, and the losses stack up. This is called generation loss. Starting from WAV means compression happens only once, at your final export, in whatever format your project needs.
WAV also cuts cleanly. MP3 files can carry a short stretch of encoder padding at the start, which can throw off tight edits or sync against picture. A WAV starts where the audio starts, so lining up a line of narration with a cut or a music beat is more predictable.
A workflow for a video or audio editor
Generate the full script as WAV, then drop it onto the timeline in your video editor or audio editor. If you want each line as its own clip, either generate lines separately or split the file at the pauses. Putting [pause 1s] between lines in the text box makes those split points easy to spot as flat gaps in the waveform.
Keep the voice on its own track, separate from music and effects. Apply any processing, such as a little EQ, compression, or room tone to match on-camera audio, to the WAV itself, and only export to MP3 or your platform's format at the very end. If the same video needs captions, download the SRT from the same generation; text to speech with subtitles covers keeping them in sync.
Replacing one line after the edit is locked
Scripts change late. Edit the sentence in the parts list or in the text box and regenerate; unchanged parts are reused instantly, so only the new line is made again. Download a fresh WAV, cut the replaced line out of it, and lay it over the old one in your timeline. Because it is the same voice at the same speed, it matches the surrounding narration without a noticeable seam.
Keep a note of the voice and speed you used for each project, for example 'George, 0.9×', so pickups weeks later match exactly.
When MP3 is the better choice
WAV files are much larger than MP3 for the same length of speech. If the file is the finished product, something you send to a friend, play on a phone or upload to a podcast host, MP3 is more practical and nobody will hear the difference on speech. Text to MP3 covers that case. A quick test: if you are going to open the file in an editor, take WAV; if you are going to press play, take MP3.
Voices, pacing and pronunciation
Choose from 16 English voices with American and British accents; the short listen button in the voice menu lets you compare them before any download. For narration over footage, a speed of 0.9× to 1× leaves room for the picture, and it is easier to tighten gaps in the editor than to slow speech down afterward. The YouTube guide has more on pacing a voiceover against B-roll.
Numbers, dates, units and titles are read in their spoken form automatically. If a brand or place name comes out wrong, spell it phonetically in the box and regenerate just that part before you export.
Frequently asked questions
Is WAV better quality than MP3?
WAV is uncompressed, so it keeps all of the generated audio. For casual listening you will rarely hear a difference on speech, but for editing and re-exporting WAV avoids the loss that builds up with repeated compression.
Why is the WAV file so large?
Uncompressed audio takes more space; that is the trade-off for editing headroom. Once your edit is finished, export the final version in a compressed format.
Can I import the WAV into my video editor?
WAV is a standard audio format that video and audio editors widely support. Drag it onto the timeline like any other audio clip.
Is there a watermark or attribution requirement?
No. The WAV contains only the speech you generated, with no watermark, and we do not require attribution.
Can I get a separate WAV file for each sentence?
Not automatically, since batch export is not available. Generate each line on its own, or split one WAV at the pauses in your editor.
Does my script leave my computer?
No. Everything runs in your browser and the text is never uploaded. After the first use the tool also works offline.