ElevenLabs v4AI voiceover
ElevenLabs' newest speech model narrates your Text-to-Video, Avatar and Podcast projects in 90+ languages — with audio tags for delivery and two-host dialogue for podcasts.
- Newest
- From 13 credits per 1k characters
- Does · Text → speech
- Billed per · 1k characters
ElevenLabs v4 at a glance
ElevenLabs v4 is ElevenLabs' flagship speech model. It replaced v3 in Shorz at the same price, adding languages (90+ versus 70+), more reliable audio tags, better IPA pronunciation handling and double the per-request character ceiling.
Specs in Shorz
- Made by
- ElevenLabs
- Languages
- 90+
- Per request
- Up to 10,000 characters (TTS)
- Dialogue
- Up to 10 voices, 2,000 characters across inputs
- Control
- Audio tags and IPA pronunciation
- Released
- 28 September 2026
- Your own voice
- Optional — add an ElevenLabs key for cloned voices
Price in Shorz credits
13credits per 1k characters
1 credit = €0.01. Prepaid packs, no subscription, credits never expire. Prices are read from the same live catalog the app uses. See packs
Why pick ElevenLabs v4 in Shorz
90+ languages
Narrate in the language your audience watches in.
Directable delivery
Audio tags shape tone and emphasis, and IPA fixes how names and jargon are pronounced.
Podcast dialogue
Text to Dialogue voices a multi-speaker script in one pass for two-host Podcast projects.
Captions on the word
Subtitles are timed from the same narration, word by word.
Best for
- Faceless narration
- Avatar voices
- Two-host podcasts
- Multilingual videos
Where ElevenLabs v4 works in Shorz
Same model, no separate account: it runs on your Shorz credits wherever the app offers it.
How to use ElevenLabs v4 in Shorz
Shorz is a desktop app for Windows and Mac. Download it, sign in, and ElevenLabs v4 is already in the model picker — no API key, no waitlist, no second subscription.
- 1Download Shorz for Windows or Mac and sign in.
- 2Open a Text-to-Video, Avatar or Podcast project and go to Voice.
- 3Pick a preset voice (or your cloned voice with your own ElevenLabs key).
- 4Generate — narration and word-timed captions are added to the timeline.
ElevenLabs v4 vs other voice & audio models
All voice & audio models in Shorz, with live credit prices.
| Model | Best at | Does | Billed per | Credits |
|---|---|---|---|---|
| ElevenLabs v4 | ElevenLabs' flagship text-to-speech: 90+ languages, audio tags, 10,000 characters a request. | Text → speech | 1k characters | 13 per 1k characters |
| ElevenLabs Scribe v2 | ElevenLabs' speech-to-text — word-timed transcripts behind captions, clips and B-roll. | Speech → text | Minute | 1 per minute |
| ElevenLabs Dubbing v2 | ElevenLabs' dubbing model — re-voice a video into around 108 languages with re-synced captions. | Dub → other language | Minute | 286 per minute |
| ElevenLabs Sound Effects | Describe a sound, get a sound — 0.5 to 22 second effects for any edit. | Text → SFX | Generation | 16 per generation |
| ElevenLabs Voice Isolator | Strip background noise and keep the voice — studio-clean audio from a noisy recording. | Noise → clean voice | Minute | 16 per minute |
Every model, one app
Shorz isn't a model playground. The models generate the parts; the editor around them turns those parts into a finished, captioned, published video.
- Every model on one prepaid balance — no per-provider subscriptions
- No watermark on anything you generate or export
- Full commercial rights on what you create
- No API keys to manage: the models run on your Shorz account
- New model versions appear in the picker without an app update
- Drivable from Claude, Cursor, Codex or Gemini over MCP
ElevenLabs v4 questions
Not for the preset voices — they run on your Shorz account. An ElevenLabs key is only needed to narrate with your own custom or cloned voice.
90+, up from 70+ in ElevenLabs v3.
Per 1,000 characters of script in Shorz credits; the live rate is on this page. Roughly a minute of narration per 1,000 characters.
Still have questions? Ask founder
More models in Shorz
Free on free runsElevenLabs Scribe v2
ElevenLabs · Voice & Audio
ElevenLabs' speech-to-text — word-timed transcripts behind captions, clips and B-roll.
ElevenLabs Dubbing v2
ElevenLabs · Voice & Audio
ElevenLabs' dubbing model — re-voice a video into around 108 languages with re-synced captions.
DefaultKling Avatar Pro
Kling AI · Avatar
The default talking-avatar model — Kling's Pro tier, with motion and gesture prompts.
DefaultElevenLabs Music
ElevenLabs · Music
ElevenLabs' music model — tracks of an exact length, from 10 seconds to 5 minutes.
Try ElevenLabs v4 in Shorz
Download Shorz for Windows or Mac and ElevenLabs v4 is already in the picker — no API key, no subscription, no watermark.
Publishes straight to