Text reading
"Text reading" in LmBox turns a script into speech: pick a voice, adjust speed / pitch / volume, preview the result, then Import to timeline in the connected editing app or Export audio to this computer. The sidebar icon is . To clone your own voice, use Voice replicate.
Video tutorial
What you will learn
- Enter a script and choose a reading voice and sample rate
- Adjust speed, pitch and volume, then synthesize
- Get subtitles from the timeline or import them from this computer, read them sentence by sentence and place them aligned on the track
- Preview the waveform and open the reading history
- Import to the editing timeline or export an audio file
Guide
This is the Lab guide (main document) for the LmBox desktop app. For installation see LmBox desktop install; to connect the extension see Plug-in manager. Release notes: desktop release notes (Chinese only for now).
What it solves
| Pain point | What this page does |
|---|---|
| A voice-over script needs sound fast | Enter text → synthesize → import to the timeline |
| Change the voice, speed it up or slow it down | Reading voice drawer + speed / pitch / volume sliders |
| Voice-over must line up with existing subtitles | Click Get from timeline or Import subtitles from local, synthesize per sentence, then import |
| Keep the result or move it elsewhere | The reading history keeps it; you can export the file or drag it out next to the waveform |
Before you start
- Pick the target editing app in the sidebar ( / / / Final Cut and so on), and make sure the extension icon is lit (needed to import to the timeline).
- Sign in to your LmBox account (needed for synthesis on the official route).
- Before importing to the timeline, choose a cache folder in Settings.
Desktop screen
Open from the sidebar. From top to bottom: top bar (subtitle entry) → text or subtitle list → waveform and preview (free text) → voice and parameters → Synthesize / Import / Export.
Figure: text input, waveform preview, reading voice and speed / pitch / volume, plus Synthesize / Import to timeline / Export audio. The screenshot shows the Chinese interface.
Screen areas
| Area | What it does |
|---|---|
| Top bar | Get from timeline / Import subtitles from local; once loaded it shows the line count, character count and estimated caps, and you can clear the subtitle script |
| Text box | Free text: enter the text to read; shows the character limit and billing hint |
| Subtitle list | Subtitle script: one sentence per row, editable; you can pause, resume or cancel while reading |
| Waveform preview | Preview after free-text synthesis; the clock beside it opens the Reading history |
| Reading voice | Opens the Voices and filters drawer on the right to pick a voice (see below) |
| Sample rate | For example 16000 Hz (follow the options on screen) |
| Speed / Pitch / Volume | Sliders for fine tuning; some voices also offer Reading emotion |
| Synthesize | Start generating speech |
| Import to timeline | Write the current result into the connected editing app |
| Export audio | Copy it to the location you choose on this computer |
Voice drawer (Voices and filters)
Click the Reading voice row (or the lightning button beside it) to open the Voices and filters drawer on the right:
| Action | Description |
|---|---|
| Filter | Narrow the list by Supported language, Type and Quality |
| Voice card | Shows the name, scenario tags, Standard / Premium and the multiplier |
| Preview | The play button on a card lets you hear a sample of that voice first |
| Select | Click a card to close the drawer; that voice is used for later synthesis |
Figure: the "Voices and filters" drawer on the right, with language / type / quality filters and voice-card preview. The screenshot shows the Chinese interface.
Recommended workflow
Free text
- Type the script in the box (mind the character limit).
- Click Reading voice to choose a voice, and adjust sample rate, speed, pitch and volume if needed.
- Click Synthesize and listen to the waveform to confirm.
- Click Import to timeline to place it on the timeline, or Export audio to save it to this computer; you can also drag the file out from beside the result.
- To listen to past results, click the clock beside the waveform to open the Reading history.
Voice-over by subtitles
- Click Reading voice and choose a voice.
- In the top bar click Get from timeline (the editing extension must be connected and the timeline must already have subtitles), or Import subtitles from local.
- Check each sentence in the list, then click Synthesize; the top bar shows the line count, character count and estimated caps, and you can pause, resume or cancel while reading.
- When done, Import to timeline: each sentence lands at its subtitle's start; short readings leave a gap, and overlapping sentences move to another empty track.
To voice subtitles with your own voice, use the official route in Voice replicate.
Billing (official route)
The official route uses caps by character count. For subtitle scripts, the cost is the higher of "how many sentences were read" and the character count (many short lines are billed per sentence), whatever your account level. The screen shows the estimated amount; if you do not have enough caps, top up in the app. If you are not signed in, sign in before synthesizing. If the screen offers another route such as a Keychain one, how it is billed follows the prompt shown at that time.
Reading history
After a successful synthesis it is saved automatically to the Reading history on this computer. Click an entry to listen again, or delete it (the audio on this computer is removed too). If the file was moved or deleted it may no longer play.
FAQ
Clicking "Synthesize" says to sign in first?
The official route needs you to sign in; then try again.
Import to timeline does nothing?
Finish a synthesis first, make sure the extension is connected, and that a cache folder is chosen in Settings.
Export failed?
Synthesize successfully first so it is written to the reading library, then export; check the permissions of the destination folder.
Want to use your own voice?
Go to Voice replicate in the sidebar, clone a voice, then use it in the voice-over flow.
Release notes
2.7.0Fixed the issue where importing to the timeline in newer Premiere versions could not create a new track automatically; it now tries to add a track for the drop, and tells you to add an audio track first if it cannot.2.4.2Subtitles can be taken from the timeline or imported from this computer, read sentence by sentence and placed aligned on the track; the top bar shows the line count, character count and estimated caps, the list has one sentence per row, and reading can be paused, resumed or canceled.1.9.3Waveform preview now stops when it finishes by default; a loop toggle is available beside play.0.3.0Fixed the synthesized waveform preview area being stretched too tall on the Text reading page on Windows.0.1.9Fixed an issue when importing audio to the timeline: if another Lab had been opened before, the first import could wrongly warn that it did not match the Lab on the left; you can now import directly.0.1.9Fixed an issue when connected to DaVinci Resolve: after importing reading audio several times, later imports other than the first did not land on the track; you can now import repeatedly.0.1.8Added a drag-out action beside the synthesized result, so you can drag the finished audio into a folder or another app.