PERSO DUBBING · 2026

Hear the difference. Compare the evidence.

The same films. Four dubbing services. Explore real outputs and the evidence behind translation, voice similarity, naturalness and emotion.

Sintel — Blender Foundation
Sintel · Perso Linnet4
English original · lip-sync excluded
3 original films
4 services
11 outputs · 1 failure
4 evaluation dimensions
Evaluated November 18, 2026 · Perso-authored pilot

In this pilot, Linnet4’s strength is balance.

Sintel and Cosmos received positive AI judgments for voice similarity, naturalness and emotion preservation. Explore the differences across scenes.

01Provisional editorial order

Perso Linnet4

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

generated: 3/3 · held judgments: 0
02Provisional editorial order

ElevenLabs Dubbing v2

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

generated: 3/3 · held judgments: 2
03Provisional editorial order

HeyGen Speed · Audio Only

Strong findings on Sintel; delivery and emotion differences observed on Tears of Steel.

generated: 3/3 · held judgments: 2
04Provisional editorial order

Synthesia AI Dubbing

Delivery and emotion differences observed in two completed scenes. One generation failed.

generated: 2/3 · held judgments: 1
Perso’s own three-film pilot. This is a post-evaluation editorial interpretation, not a score-based or statistically established ranking. All positions remain uncertain. Held judgments may change the order; failures are not scored as zero. Sample-specific limitations ↗

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
HeyGen Speed · Audio OnlyFirst output · no manual edits
Synthesia AI DubbingFirst output · no manual edits
Scene-level automatic measurementsRole 1 / role 2 cosineUTMOSv2 predicted mean
Perso Linnet 40.408 / 0.3022.61
ElevenLabs Dubbing v20.470 / 0.2702.23
HeyGen Speed · Audio Only0.495 / 0.2012.76
Synthesia AI Dubbing0.322 / 0.2482.50
Tears of Steel
Tears of Steel — Blender Foundation

Tears of Steel

English original · lip-sync excluded
ElevenLabs Dubbing v2First output · no manual edits
HeyGen Speed · Audio OnlyFirst output · no manual edits
Synthesia AI DubbingGeneration failed · HTTP 500 · quality N/A
Scene-level automatic measurementsRole 1 / role 2 cosineUTMOSv2 predicted mean
Perso Linnet 40.432 / 0.4252.14
ElevenLabs Dubbing v20.492 / 0.3652.18
HeyGen Speed · Audio Only0.279 / 0.364 †2.80
Synthesia AI DubbingN/AN/A
Cosmos Laundromat
Cosmos Laundromat — Blender Foundation

Cosmos Laundromat

English original · lip-sync excluded
ElevenLabs Dubbing v2First output · no manual edits
HeyGen Speed · Audio OnlyFirst output · no manual edits
Synthesia AI DubbingFirst output · no manual edits
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
HeyGen Speed · Audio Only0.385 / 0.1873.06
Synthesia AI Dubbingheld judgments2.92

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.

MQM error categories

Mistranslation, omission and addition categories guided transcript review. AI observations of preserved meaning concern cited examples, not 100% translation accuracy or formal human MQM scores.

Methodology source ↗

Speaker cosine · UTMOSv2

ECAPA embeddings compare selected corresponding speech segments. UTMOSv2 predicts quality of the full audio mix across five fixed-seed runs. Neither establishes overall dubbing superiority.

Methodology source ↗

ITU-T P.808 · human evaluation

This international recommendation addresses subjective speech-quality evaluation. Our AI pilot is not a P.808 human study or certification. Bilingual listening review remains a follow-up.

Methodology source ↗

SpeechBrain ECAPA ↗

Sample-specific limitations

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.

HeyGen · Tears of Steel: role 1 ends at 13.3 s; two transcriptions place the next speaker at 13.0 s and 13.68 s. The segment may mix speakers.

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.

Were the conditions comparable?

We used the same three English originals, first outputs, no manual translation edits or glossary, and no lip-sync. Perso, ElevenLabs and HeyGen used Mexican Spanish; Synthesia used Spanish without a region choice. This is not a comparison of every provider’s highest-tier model.

How was brand bias addressed?

Gemini received original and dubbed audio without brand names, video or transcripts. Identical-audio, silence and mismatch controls checked input handling, not general judging validity. Perso’s role, five held judgments and one generation failure are disclosed.

Why is the order provisional?

The experiment did not calculate an overall ranking. The editorial order was added on November 18, 2026 for this comparison page. All completed outputs had example-level observations of preserved translation; that does not distinguish a winner. More source films and blinded bilingual review are needed.

Explore detailed comparisons

ElevenLabs ↗HeyGen ↗Synthesia ↗Rask ↗

Now try your own video.

Listen to the samples, then explore dubbing with Perso.

Explore Perso Dubbing ↗

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