Skip to main content

​
Overview

ElevenLabs provides the text-to-speech models in varg. Multiple model variants are available balancing quality, speed, and language support.
Model IDQualitySpeedLanguagesCredits~Cost
eleven_v3BestStandardMulti25$0.25
eleven_multilingual_v2GreatStandard29 languages25$0.25
turboGoodFastestEnglish20$0.20
eleven_turbo_v2GoodFastEnglish20$0.20
eleven_turbo_v2_5GoodFastMulti20$0.20
eleven_flash_v2GoodUltra-fastEnglish20$0.20
eleven_flash_v2_5GoodUltra-fastMulti20$0.20

​
Quick start

import { createVarg } from "vargai/ai"

const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

const result = await varg.speechModel("eleven_v3").generate({
  text: "Welcome to varg, the AI video generation platform.",
  voice: "rachel",
})

console.log(result.audio.url)

​
Available voices

VoiceGenderStyleBest for
rachelFemaleCalm, warmNarration
bellaFemaleSoft, gentleStorytelling
domiFemaleConfidentPresentations
elliFemaleYoung, cheerfulSocial media
adamMaleDeep, warmNarration
joshMaleYoung, energeticSocial media
samMaleRaspyCharacter voices
antoniMaleCalmPodcasts
arnoldMaleAuthoritativeAnnouncements
Any valid ElevenLabs voice_id works. The names above are convenience aliases for built-in voices. Browse more at ElevenLabs Voice Library.

​
Parameters

​
text
string
required
The text to convert to speech.
​
voice
string
default:"rachel"
Voice name or ElevenLabs voice ID.
​
model
string
default:"eleven_multilingual_v2"
Speech model variant (see table above).
​
provider_options
object
stability — 0 to 1 (default 0.5). Higher = more consistent, lower = more expressive. similarity_boost — 0 to 1 (default 0.75). How closely to match the voice.

​
Choosing a model

ScenarioRecommended model
Best quality Englisheleven_v3
Multiple languageseleven_multilingual_v2
Fast English narrationturbo or eleven_turbo_v2
Real-time / interactiveeleven_flash_v2_5
Budgetturbo (20 credits)

​
Composition example

Use speech in a video composition with captions: 
const narration = Speech({
  model: varg.speechModel("eleven_v3"),
  text: "This product will transform your workflow.",
  voice: "adam",
})

<Clip duration={5}>
  <Video model={varg.videoModel("kling-v3")} prompt="product showcase" duration={5} />
  {narration}
  <Captions source={narration} />
</Clip>

​
Pricing

ModelCreditsUSD
eleven_v325$0.25
eleven_multilingual_v225$0.25
turbo / eleven_turbo_v220$0.20
eleven_turbo_v2_520$0.20
eleven_flash_v2 / v2_520$0.20

VEED Fabric

Animate a portrait with generated speech.

Sync Lipsync

Apply speech to existing video.

Whisper

Transcribe audio back to text.