When Multilingual AI Companions Lose Character Voice After Translation

Focus query: multilingual AI companion character voice drift

This open worksheet turns a narrow adult-AI quality question into a reproducible review. It uses only synthetic adult identities and separates observed behavior from product claims. A reviewer should publish the complete denominator, failed cases, account tier, date, and configuration rather than reporting only a favorable example.

Research question

Does an AI companion preserve character voice, relationship distance, idiom, and factual state after language switching or translation?

Controlled setup

Define an adult fictional character with language-specific address terms, politeness level, four voice markers, and five facts that must survive switching between English, Chinese, Japanese, and Korean.

Test protocol

  1. Run a baseline scene in the source language and mark the expected voice features.
  2. Switch languages without rewriting the character card and test factual recall.
  3. Return to the source language and check whether translated phrasing has contaminated the original voice.
  4. Test relationship distance, honorifics, pronouns, idiom, and refusal wording separately.
  5. Have a native reviewer explain each failed score rather than relying on automatic translation similarity.

Scoring rubric

MetricOperational definitionRecord
Fact preservationStable facts retained after language switching0-4 plus written evidence
Voice retentionLanguage-specific character markers retained0-4 plus written evidence
Relationship distanceExpected formality and address maintained0-4 plus written evidence
Translation contaminationSource-language voice replaced by translated templates0-4 plus written evidence
Native-review agreementIndependent reviewers reach the same conclusion0-4 plus written evidence

Use 0 for a material failure, 1 for mostly failing, 2 for mixed behavior, 3 for a repeatable pass with minor defects, and 4 for a repeatable pass with clear evidence. Never replace the raw count with the average score.

Downloadable evidence schema

Download the blank CSV test template. Each row records a case ID, stage, controlled variable, expected result, observed result, metric, numeric score, evidence reference, hard-failure flag, and reviewer note. The file is intentionally blank: it is a protocol asset, not a fabricated benchmark.

Hard-failure rule

A hard failure occurs when language switching changes identity or relationship state, introduces a prohibited stereotype, or converts a clear boundary into ambiguous wording.

Publication checklist

How to interpret the result

A passing score answers only the research question under the recorded conditions. It does not establish that a product is universally better, fully private, completely uncensored, or appropriate for every use. Compare methods and evidence before comparing averages. When two products use different account tiers or generation modes, report them as separate conditions rather than forcing a single ranking.

FAQ

Is this an independent Ponys.ai review?

No. This is a transparent, team-maintained test method. Independent publishers may reuse the blank protocol and should disclose their own methods and relationships.

Can the score be used as a marketing claim?

Only with the test date, denominator, configuration, and evidence. A number without those fields is not reproducible.

Why use synthetic adult cases?

They reduce privacy and likeness risk while making expected facts, identities, and boundaries explicit.

What should be cited?

Cite the protocol URL for the method and the publisher's own dated results page for observed findings. Do not cite the blank CSV as if it contained measured results.

Relevant product paths for testing


Disclosure: Published and maintained by the Ponys.ai team. This page provides an original test method and blank evidence format, not an independent rating.

Ponys.ai resource index