Audio model · by ElevenLabs

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 19 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
Upload a recording instead of a preset voice

Price in Shorz credits

19credits 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 AI 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

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.

  1. 1Download Shorz for Windows or Mac and sign in.
  2. 2Start a Text-to-Video, Avatar or AI Podcast project. The chat asks for your script.
  3. 3Pick a preset voice on the Voice card, or upload your own recording.
  4. 4Create the video. Narration and word-timed captions are added for you.

ElevenLabs v4 vs other voice & audio models

All voice & audio models in Shorz, with live credit prices.

ModelBest atDoesBilled perCredits
ElevenLabs v4ElevenLabs' flagship text-to-speech: 90+ languages, audio tags, 10,000 characters a request.Text → speech1k characters19 per 1k characters
ElevenLabs Scribe v2ElevenLabs' speech-to-text — word-timed transcripts behind captions, clips and B-roll.Speech → textMinute1 per minute
ElevenLabs Dubbing v2ElevenLabs' dubbing model — re-voice a video into around 108 languages with re-synced captions.Dub → other languageMinute418 per minute
ElevenLabs Sound EffectsDescribe a sound, get a sound — 0.5 to 22 second effects for any edit.Text → SFXGeneration23 per generation
ElevenLabs Voice IsolatorStrip background noise and keep the voice — studio-clean audio from a noisy recording.Noise → clean voiceMinute23 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

No. Every voice runs on your Shorz account and is paid with Shorz credits. No API key is needed.

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