Text to Speech
Generate spoken audio from a script. Paste text on the module; billed by character count.
Generation module
Text to Speech
Turn a script into a spoken take for demos, voice-over beds, and localization drafts. Credits follow character count, not track duration - paste the text, pick language and voice, download the WAV.
What you get
- Speech (WAV)
- Localized speech (WAV)
Ready workflows that use Text to Speech
These templates open pre-wired on the canvas with this module already connected.
How it works
Open the Workflow Builder
Drag the module onto the canvas - alone between Input and Output, or wired into a longer chain.
Configure and upload
Adjust the module's settings, add your file, and check the credit quote before running.
Collect the results
Outputs land in your Audio Tools library - audio downloads directly, data opens in interactive viewers.
Run Text to Speech on your track
Open the Workflow Builder, drop the module on the canvas, and see the credit quote before anything runs.
Open Workflow BuilderFrequently asked questions
What does the Text to Speech module output?
Speech (WAV); Localized speech (WAV). Audio outputs are saved to your Audio Tools library and download as high-quality files.
Can I combine Text to Speech with other modules?
Yes. Text to Speech is one of 60+ professional modules on the Workflow Builder canvas - wire it before or after stem separation, mastering, transcription, effects, and localization modules and run everything as one job on a single upload.
How is Text to Speech billed?
With Credits - the same pool as the rest of the suite. Credits scale with track length, the full quote is shown before anything runs, and failed jobs are refunded automatically.
Do I need to install anything?
No. Everything runs in the cloud from your browser. Common formats like WAV, AIFF, FLAC, and MP3 are supported.