Text-to-speech

Generate placeholder voice-over for your Lines. Poneglyph reads each Translation aloud with a synthetic voice and saves it as a .wav file. Use it to hear pacing and timing before real recordings exist.

Note

Text-to-speech needs a workspace checked out so the audio has somewhere to go. Set the voice and engine in File ▸ Settings ▸ Text To Speech first.

Generate placeholder audio

1. Open the exporter from Export ▸ Export .wav.
2. Pick the languages and Folders to cover.
3. Use the Filter bar to narrow down to the Lines you want.
4. Start the export.

The work runs in the Job Center, so you can keep editing while it finishes. Each Line gets one .wav file per language.

Where the files land

Generated audio does not go in your normal audio folder. It lands in a separate diverted-originals path, set up by your Manager. This keeps placeholder voice-over apart from real recordings so the two never get mixed up.

To find a file, right-click a Translation and pick the From Diverted Originals entry. That opens the generated .wav.

See which Lines have TTS

Each Translation shows a recording status. After you generate audio, the status flips from No TTS to TTS. Scan the column to see at a glance which Lines have placeholder voice-over and which still need it.

📷 Screenshot: TTS status indicator on a Line

A Line whose recording status reads TTS next to one that still reads No TTS.

Tip

When real recordings arrive through audio import, the status moves on from TTS to a recorded state. That tells you the placeholder has been replaced.