← Compare all services
PERSO DUBBING · 2026

Perso Dubbing vs. ElevenLabs

Listen to Perso Linnet4 and ElevenLabs on the same three films. Compare Spanish dubbing, inspect the AI observations, then choose the workflow that fits your video.

Sintel — Blender Foundation
Sintel
English original · lip-sync excluded
3 original films
Perso Linnet4
ElevenLabs Dubbing v2
4 evaluation dimensions
Evaluated November 18, 2026 · Perso-authored pilot

AI observations, by scene

This is a Perso-authored pilot, not an independent certification or a statistically established winner. AI labels describe these samples only. Held judgments and failed outputs remain visible.

Perso Linnet4

Positive judgments across voice, naturalness and emotion in two scenes.

generated: 3/3 · held judgments: 0

ElevenLabs Dubbing v2

Strong findings on Sintel; emotion preservation stood out on Tears of Steel.

generated: 3/3 · held judgments: 2

Listen before you decide.

Compare the original with each first output. Playing one sample pauses the others. Open a film to explore its samples and measurements.

Sintel
Sintel — Blender Foundation

Sintel

English original · lip-sync excluded
ElevenLabs Dubbing v2First output · no manual edits
AI observations, by scenePerso Linnet4ElevenLabs
TranslationMeaning preserved in cited examplesMeaning preserved in cited examples
Voice similarityStrong similarityStrong similarity
NaturalnessNo clear artifacts detectedNo clear artifacts detected
EmotionEmotion preservedEmotion preserved
Scene-level automatic measurementsRole 1 / role 2 cosineUTMOSv2 predicted mean
Perso Linnet 40.408 / 0.3022.61
ElevenLabs Dubbing v20.470 / 0.2702.23
Tears of Steel
Tears of Steel — Blender Foundation

Tears of Steel

English original · lip-sync excluded
ElevenLabs Dubbing v2First output · no manual edits
AI observations, by scenePerso Linnet4ElevenLabs
TranslationMeaning preserved in cited examplesMeaning preserved in cited examples
Voice similarityPartial similarityJudgment withheld
NaturalnessMinor artifactsMinor artifacts
EmotionPartial emotion shiftEmotion preserved
Scene-level automatic measurementsRole 1 / role 2 cosineUTMOSv2 predicted mean
Perso Linnet 40.432 / 0.4252.14
ElevenLabs Dubbing v20.492 / 0.3652.18
Cosmos Laundromat
Cosmos Laundromat — Blender Foundation

Cosmos Laundromat

English original · lip-sync excluded
ElevenLabs Dubbing v2First output · no manual edits
AI observations, by scenePerso Linnet4ElevenLabs
TranslationMeaning preserved in cited examplesMeaning preserved in cited examples
Voice similarityStrong similarityJudgment withheld
NaturalnessNo clear artifacts detectedMinor artifacts
EmotionEmotion preservedPartial emotion shift
Scene-level automatic measurementsRole 1 / role 2 cosineUTMOSv2 predicted mean
Perso Linnet 40.589 / 0.255 †2.54
ElevenLabs Dubbing v20.563 / 0.4492.34

Cosine is not a probability; UTMOSv2 is not human MOS. Background audio and short segments affect these diagnostics. They are not combined into ranking scores. Speaker boundaries may be uncertain.

Methods, measurements and limitations. All open.

We distinguish recognized evaluation frameworks, reproducible automatic measurements and AI interpretation. These results are not an independent certification.

Perso · Sintel: the AI explanation refers ambiguously to speakers. Its positive voice-similarity label is retained with this warning, not treated as verified speaker identity.

Perso · Cosmos: role 2 cosine is 0.255 against the original role and 0.244 against the other role. Interpretation is withheld; this cannot establish voice preservation or a speaker swap.

How we evaluated ↗

Workflow and purchasing considerations

The product and pricing information below concerns available workflows and plans. It is not the cost or quality score of the Linnet4 sample test. Check current rates, model access, lip-sync and revision limits before purchasing.

Evaluated November 18, 2026 · Perso-authored pilot
Tears of Steel / Sintel: Blender Foundation, CC BY 3.0. Cosmos Laundromat: Blender Foundation, CC BY 4.0.
Sintel · Tears of Steel · Cosmos Laundromat

Features, side by side

Compare the specific product and plan. On mobile, swipe the table sideways to see both tools.

Published capabilities · Reviewed September 14, 2026
FeaturePerso DubbingElevenLabs
Product comparedAI DubbingDubbing v2
Existing video inputYesYes; translates the audio
Source-video lip-syncLip-dubbing supportedNot part of Dubbing; available elsewhere via third-party models
Multiple source voicesSpeaker detection and voice preservationSpeaker detection and voice preservation
Edit a generated dubScript review; verify regeneration usageNo in-app editor; Enterprise API editing
OutputVideo and supported audio/script downloadsSingle lossless audio file
Legacy product distinctionCheck the selected output modeDubbing Studio v1 offers editing and multiple export formats

Dubbing v2 and legacy Studio are different products

Dubbing v2 provides automatic translation with speaker detection and returns a single lossless audio file. It has no in-app transcript editor; Enterprise plans support transcript editing and regeneration through the API. Legacy Dubbing Studio uses v1, remains in maintenance mode and supports MP4, AAC, AAF, SRT and separate speaker WAV exports.

Which one fits your team?

Choose Perso Dubbing

Choose Perso Dubbing when you want to upload existing footage, review the script and create a dubbed video with lip-dubbing in one workflow. Confirm your language pair, clip length and download requirements on a test project.

Choose ElevenLabs

Choose ElevenLabs when translated audio is the main deliverable or your production already uses its voice tools and APIs. If you need detailed editing, distinguish legacy Dubbing Studio from v2 and verify Enterprise API access.

Pricing & allowances

Perso Dubbing offers Finch dubbing from $0.11/min on PRO monthly: $99/month for 10,800 credits, or up to 900 minutes at full Finch allocation. Actual minutes depend on the model and other credit use. Optional lip sync has separate usage conditions. ElevenLabs charges dubbing by source duration and target language, with rates depending on the model. Include any additional video assembly or lip-sync workflow in a like-for-like estimate.

Use source duration × target languages, then account for lip-sync, revisions and plan limits. Monthly billing and annual promotions are different commitments. Prices and allowances can change.

Questions, answered

Does ElevenLabs support lip-sync?

Lip-sync is not part of ElevenLabs Dubbing. ElevenLabs documents lip-sync in other products through third-party models. This comparison evaluates Dubbing v2, not every tool on the platform.

Can ElevenLabs export separate speaker tracks?

Legacy Dubbing Studio supports separate speaker WAV tracks and formats including MP4 and SRT. Dubbing v2 returns a single lossless audio file. Check which model your workflow uses.

Can I try Perso before subscribing?

Perso offers a free trial. Check the current pricing page for trial credits, output limits and access to lip-dubbing before starting your test.

How should I compare dubbing quality?

Use the same source clip, language pair and output settings. Review names, translation meaning, voice consistency and visible lip movements. Include more than one speaker when that matches your real workload.

How do I move an existing project?

Start with your original source video and approved transcript. Upload the source, choose a supported target language, review the generated script and create a test output. Check file limits and export requirements before moving a full library.

Sources & further reading

Prepared by Perso Dubbing. Product information was checked against the official pages below on September 14, 2026. Confirm current availability and usage rules before purchasing.