Strella docs
GuidesDeveloper
Strella docs
GuidesDeveloper
Welcome to StrellaChangelog
Run your first studyHow AI helps you in StrellaGlossary
The Build screenStart with the study setup chatSet up your study detailsWrite research objectivesBuild your screenerBuild your question guideBest practicesAdd survey questions to your interviewAdd a stimulus to your interviewHost a prototype and add it to your interviewAdd a card sortAdd a tree testRandomize sections (A/B variants)Conditional sectionsVersion historyUse the build assistantPreview your interviewUpload an existing discussion guideImport from another study
How the AI moderator worksVoice, language & behaviorRecording modesCustom dictionary & pronunciationCustomize the participant experienceWhat the AI moderator can't do
How recruitment worksSchedule moderated interviewsHire from a participant panelBring your own participantsManage share links & redirectsPass data with URL parametersControl access & schedulingSet quotasApprove, reject & invitePay participants you recruitedReport a participantWatch the funnel
Publish your studyEdit a study after launch
Get oriented in ResultsBring in interviews you ran elsewhereReview a single interviewBrowse analysisCode responsesSee how participants complete on-screen tasksSee how participants sorted your cardsSee how participants use your Figma prototypeUse Strella's AI chatAI chat best practices
Build & share a reportCreate & share a highlight reel
Teammates, organizations & workspacesDelete projectsProject defaultsBilling & creditsConnect FigmaAPI, MCP & AI assistantsParticipant data accessMedia links and who can open themActivity logs
Step typesScreener question typesRecording settingsParticipant statuses & funnel stagesSupported languagesVoice optionsBrowser & device requirements
MCP serverConnect an AI clientTools & skills referenceUse cases & example promptsWhat's newSecurity & privacyFAQ & troubleshooting
ReferenceVoice options
Reference

Voice options

Voices come from four providers. Each has different strengths in quality, expressiveness, and language coverage.

The voice picker in Settings → AI moderator groups voices by provider. Use this reference to choose a provider for your needs.

ProviderStrengthsSpeed range
OpenAIWidest language support, consistent quality.0.5× to 2.0×
InworldExpressive voices, limited language coverage.0.5× to 1.5×
ElevenLabsPremium quality, good multilingual support.0.7× to 1.2×
CartesiaFast, natural-sounding voices, wide language support.0.5× to 2.0×

How the voice picker works

The picker filters to voices appropriate for your study's language settings:

  • One English study: every English voice across all providers, browsable by name.
  • One non-English study: voices filter to ones that speak that language.
  • Multiple languages or all-languages: pick a gender (Feminine, Masculine, or Neutral); Strella selects the right voice per language at interview time.

You can preview any voice with the play icon. Strella reads a sample line so you can hear the timbre and pacing before committing.

Things to know

  • Participants can adjust playback speed themselves during the call, within the provider's range. Your setting is the default.
  • Spanish (Colombia) has its own Inworld voices. Pick es-CO and Inworld offers only Mateo (masculine) and Sofia (feminine). Studies in plain Spanish keep Inworld's other Spanish voices and don't get these two. OpenAI voices work for Spanish (Colombia) too, but Google, ElevenLabs and Cartesia voices don't.
  • Inworld voices won't appear for languages they don't support. The picker hides them; you don't have to figure out compatibility manually.
  • Some voices are gated behind feature access. If you don't see ElevenLabs voices, your organization may not have them enabled yet. Contact your account team.

Related

Voice, language & behavior

How to pick a voice for your study.

Supported languages

The full language list.

Supported languages

The languages the AI moderator can run interviews in. Pick one or many in Settings → AI moderator.

Browser & device requirements

What participants need to take part. What you need to author and review.

On this page

How the voice picker worksThings to knowRelated