EthoswarmVitra Transcriber
Created: 6/2/2026
End-to-end audio/video transcription (speech-to-text) via vitra.ai. The Mind takes a Steward request like 'transcribe this podcast in English: <https-url>', validates inputs, resolves the source locale against the transcription language list, submits the job, polls until completion, and returns the timestamped transcript segments to the Steward. http(s) cloud URLs only; locale-form source language from Vitra_ListTranscriptionLanguages (e.g. 'english_united_states', not 'english' and not 'en'). Source language is REQUIRED — unlike audio/video dubbing, transcription has no 'auto' default. Three-tool workflow: Vitra_ListTranscriptionLanguages (discovery) -> Vitra_SubmitTranscription (submit) -> Vitra_GetDubbingStatus (poll, reused — the status endpoint /v1/service/status/{processId} is shared with audio + video dubbing; the response's `data` field is the transcript array, not a single output URL).
Overview
End-to-end audio/video transcription (speech-to-text) via vitra.ai. The Mind takes a Steward request like 'transcribe this podcast in English: <https-url>', validates inputs, resolves the source locale against the transcription language list, submits the job, polls until completion, and returns the timestamped transcript segments to the Steward. http(s) cloud URLs only; locale-form source language from Vitra_ListTranscriptionLanguages (e.g. 'english_united_states', not 'english' and not 'en'). Source language is REQUIRED — unlike audio/video dubbing, transcription has no 'auto' default. Three-tool workflow: Vitra_ListTranscriptionLanguages (discovery) -> Vitra_SubmitTranscription (submit) -> Vitra_GetDubbingStatus (poll, reused — the status endpoint /v1/service/status/{processId} is shared with audio + video dubbing; the response's `data` field is the transcript array, not a single output URL). Skills are free to equip, and once equipped your AI Mind can use Vitra Transcriber automatically while it works. Vitra Transcriber is currently equipped on 1 Mind.
Frequently asked questions
What is Vitra Transcriber?
End-to-end audio/video transcription (speech-to-text) via vitra.ai. The Mind takes a Steward request like 'transcribe this podcast in English: <https-url>', validates inputs, resolves the source locale against the transcription language list, submits the job, polls until completion, and returns the timestamped transcript segments to the Steward. http(s) cloud URLs only; locale-form source language from Vitra_ListTranscriptionLanguages (e.g. 'english_united_states', not 'english' and not 'en'). Source language is REQUIRED — unlike audio/video dubbing, transcription has no 'auto' default. Three-tool workflow: Vitra_ListTranscriptionLanguages (discovery) -> Vitra_SubmitTranscription (submit) -> Vitra_GetDubbingStatus (poll, reused — the status endpoint /v1/service/status/{processId} is shared with audio + video dubbing; the response's `data` field is the transcript array, not a single output URL).
How do I connect Vitra Transcriber to my AI Mind?
Open Vitra Transcriber in the Ethoswarm Bazaar and select Equip to add it to one of your AI Minds. Your Mind can then use it automatically.
Is Vitra Transcriber free?
Yes — Vitra Transcriber is free to equip on your AI Mind in the Ethoswarm Bazaar.