ElevenLabs Dubbing PT-BR Audio
ElevenLabs Audio Dubbing is the AI dubbing model in FluxoKit's browser studio that translates spoken audio into another language while keeping the original voice. It bills per run by the source audio duration, about 59 credits per minute at standard quality, on plans starting at $14 per month with no ElevenLabs account.
Overview
ElevenLabs Audio Dubbing answers a localization question the voice models do not: not read me this script, but say THIS recording in another language, in the same voice. Feed it spoken audio and it returns the translated version with the original speaker's timbre preserved. FluxoKit runs it in the browser with credit pricing and no ElevenLabs account.
The dubbing space online is full of vendor marketing and almost no worked examples with real costs. This page documents the parameters, the language targets, and the per-minute credit cost up front. A source and dubbed audio pair is being produced for a later batch, so this page does not claim example clips it does not yet have.
What you can build with ElevenLabs Audio Dubbing
Audio Dubbing closes the localization loop: record or generate a narration in English, then deliver the Brazilian Portuguese version without re-recording, in the same voice. The model clones the speaker's characteristics into the target language, so a podcast segment, an ad read, or a course lesson keeps its original identity across markets. Portuguese is the default target, and the active source and target languages appear in the parameter selector on this page.
In the FluxoKit canvas the source can be an uploaded file or the audio output of a voice node, so a script generated by Multilingual v2 or Eleven v3 can flow straight into a dub. The before and after pair that demonstrates this end to end lands with a later batch; today the page documents the contract rather than showing creative it does not have.
Where ElevenLabs AI dubbing earns its credits
Billing is proportional to the duration of the source audio, about 59 credits per minute at standard quality and scaling per second, so a 30-second clip costs roughly 30 credits and every run shows its exact cost in your history. The per-minute figure on this page is the number the dubbing marketing pages never print.
Course creators, podcasters, and ad teams use dubbing to open a second-language market from content they already own, keeping the voice they built an audience on. When the source is a video rather than a bare audio track, Video Dubbing is the sibling that re-syncs the translated speech onto the footage.
ElevenLabs Audio Dubbing vs Multilingual v2 and Video Dubbing
When you have the script as text rather than a recording, generating straight into the target language with Multilingual v2 is cheaper than dubbing. Use Audio Dubbing only when you already have spoken audio to convert.
Video Dubbing is the variant for when the source is a video: it translates the speech and re-syncs it onto the footage. Audio Dubbing handles a bare audio track and returns audio.
Eleven v3 generates a fresh expressive performance from a written script. Audio Dubbing instead preserves an existing speaker's voice while changing the language.
Capabilities
Audio support
Yes
Source audio input
Yes
Dubbing
Yes
Brazilian Portuguese
Yes
Brazilian Portuguese
Yes
Output type
Audio
Default duration
60 s
Parameters and inputs
Each field below shows what the model accepts and the limits to apply.
Parameters
Audio
audio
- Required
- Yes
- Default
- Not set
- Accepts
- audio/*
Target Lang
target_lang
- Required
- No
- Default
- pt
Options
- Pt (pt)
Source Lang
source_lang
Frequently asked questions
›How much does ElevenLabs Audio Dubbing cost per minute?
Dubbing bills per run in proportion to the source audio duration, about 59 credits per minute at standard quality and scaling by the second, so a 30-second clip is roughly 30 credits. Every run shows its exact credit cost in your history, on plans from $14 per month with no separate ElevenLabs subscription.
›Does ElevenLabs Audio Dubbing really keep the original voice?
Yes. The model clones the original speaker's vocal characteristics into the target language, so the result sounds like the same person now speaking, for example, Portuguese. That voice-preserving behavior is the whole point of dubbing over generating a new narration.
›What languages can ElevenLabs Audio Dubbing use as source and target?
The active source and target languages appear in the parameter selector on this page, which reflects the live API contract in FluxoKit, with Brazilian Portuguese as the default target. Check the selector for the current list rather than assuming a fixed set.
›Do I need an ElevenLabs account to use Audio Dubbing?
No. FluxoKit runs Audio Dubbing and more than 100 other AI models under one subscription with credit based pricing and a 30-day money-back guarantee, no ElevenLabs account or API key.
Start creating
Run ElevenLabs Dubbing PT-BR Audio in your browser. No API key, no provider account.
Open a second-language market in the same voice. One studio, more than 100 AI models.
- More than 14,000 generations delivered
- Your first paid subscription includes a 30-day satisfaction guarantee, subject to the Refund Policy.
- Checkout through Stripe, cancel anytime