Text to speech
Write the voice script, then hear it read
Text to Speech and Video Voiceover turns any text into a voice script timed to the length you need, marked with pauses, stressed words, and pronunciations, with three voice directions. It then voices the script as narration, an ad or promo voiceover, a solo podcast, an audiobook chapter by chapter, or a multi-voice cast, in a library voice or a voice clone of your own voice, as MP3 audio with an optional subtitle file. Text to Speech and Video Voiceover works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Text to Speech and Video Voiceover and tell me when I need to sign in: https://beatra.ai/skills/voiceover-director/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.Docs ↗
Text in, voiceover out
The script arrives first
Pauses, stressed words, pronunciations, a timing table, and three voice directions come in the first reply.
One voice for the piece
Narration, ads, promo films, short-video reads, a solo podcast, and an audiobook in the voice you pick.
Your voice, or a whole cast
A clean recording of your own voice becomes a voice you can reuse, and each speaker in a dialogue gets a voice.
How it is made
A script timed for the ear
Each sentence carries pauses, stressed words, and pronunciations, with a timing table and three voice directions.
Short pauses and long pauses marked · Readings for hard words · Three directions set apart by age, texture, or mood
The voice you picked
Narration, ads, promo films, a solo podcast, and an audiobook, read in a catalog voice or a clone of your own.
A voice for every speaker
Dialogue and audio drama arrive as numbered clips in script order, each labelled with its speaker.
Voiceover people publish
Video voiceover
Ad, promo, and short-video narration timed to the length you need, with a subtitle file beside the audio when you want one.
Solo podcasts
Opener, sections, and closer in one host voice, with intro and outro music as their own files.
Audiobooks
A short sample passage, then the book chapter by chapter in one voice.
Multi-voice dialogue
Each speaker's lines as numbered clips in script order, ready to line up in an editor.
Inputs and outputs
Input · Text — The text to read, or a subject to write about, with length, purpose, and tone
Input · Audio — Clean recording of your own voice (optional)
- Formats
- MP3, WAV
- Specifications
- 10–300 s; up to 20 MB each
Output · Text — Timed voice script marked with pauses, stress, and pronunciations, plus three voice directions
- Specifications
- editable
Output · Audio — Voiceover, podcast, audiobook chapters, or one numbered clip per line for a cast
- Formats
- MP3
Output · Audio — Podcast intro and outro music as separate files (optional)
- Formats
- MP3
Output · Text — Subtitle file for a video voiceover (optional)
- Formats
- SRT, VTT
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Text — The text to read, or a subject to write about, with length, purpose, and tone | — | — |
| Input | Audio — Clean recording of your own voice (optional) | MP3, WAV | 10–300 s; up to 20 MB each |
| Output | Text — Timed voice script marked with pauses, stress, and pronunciations, plus three voice directions | — | editable |
| Output | Audio — Voiceover, podcast, audiobook chapters, or one numbered clip per line for a cast | MP3 | — |
| Output | Audio — Podcast intro and outro music as separate files (optional) | MP3 | — |
| Output | Text — Subtitle file for a video voiceover (optional) | SRT, VTT | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What is in the voice script?
Each sentence carries pauses, stressed words, and pronunciations, with a timing table and three voice directions.
Can it read an ad, a podcast, and an audiobook?
Yes. It voices narration, ads, promo films, a solo podcast in one host voice, or an audiobook read chapter by chapter.
Can the voiceover use my own voice?
Yes. A clean recording of your own voice becomes a voice clone you can reuse for any of these.
How does a dialogue arrive?
Each speaker has a voice, and the lines arrive as numbered clips in script order, labeled with the speaker, ready to assemble in an editor.
Does a video voiceover come with subtitles?
Yes, when you want them. A subtitle file comes with the audio.
Related Skills
