5 voice & audio models

Voice and audio models forevery soundtrack

ElevenLabs narrates, transcribes and generates sound effects in the app. Through MCP it also dubs and cleans up noisy voices. All on one balance.

Compare voice & audio models

Credit prices are read live from the same catalog the app bills from (1 credit = $0.01).

ModelBest atDoesBilled perCredits
ElevenLabs v4ElevenLabs' flagship text-to-speech: 90+ languages, audio tags, 10,000 characters a request.Text → speech1k characters16 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 languageMinute352 per minute
ElevenLabs Sound EffectsDescribe a sound, get a sound — 0.5 to 22 second effects for any edit.Text → SFXGeneration20 per generation
ElevenLabs Voice IsolatorStrip background noise and keep the voice — studio-clean audio from a noisy recording.Noise → clean voiceMinute20 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

AI voice & audio models questions

No. Preset voices, transcription, dubbing, sound effects and voice isolation all run on your Shorz account. No API key is needed.

Scribe v2 transcribes the audio with word-level timing, so subtitles land on the spoken word — including after dubbing into another language.

Still have questions? Ask founder