Jump to section

Or jump from this list on a smaller screen.

This is a page from the Audivra documentation. Developer exports — index: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.

Speech to text

Transcribe uploaded audio or a public audio URL. Credits are billed per second of recognized duration.

Try it

Upload a short clip — same contract as POST /api/v1/stt.

Try it

Upload a short clip. Session cookie or a pasted sk_live_ key both work.

API key (optional if signed in)

Checking session…

Audio

Language

POST

/api/v1/stt

Auth required

Multipart field audio, or JSON audio_url (SSRF-checked). Meters 5 credits per ceil(second). Duration and upload size follow the caller plan.

Parameters

Name	Type	Required	Description
audio	file	No	WAV, MP3, M4A, OGG, FLAC, or WebM (multipart)
audio_url	string	No	Public https URL — private hosts are rejected
language	string	No	auto or allowlisted ISO 639-1 code (en, de, it, nl, fr, es, pt, pl, ru, uk, tr, sw, … (33 total))

Request body

JSON

{
  "audio_url": "https://cdn.example.com/clip.wav",
  "language": "de"
}

Response

JSON

{
  "text": "Willkommen bei Audivra",
  "language": "de",
  "duration_seconds": 2.4,
  "engine": "faster-whisper:tiny",
  "credits": 15,
  "words": []
}

Errors

Status	Meaning
401	Unauthorized
402	Credit quota exceeded
422	No speech detected
503	Whisper engine not installed on the inference worker

Allowlisted languages

33 target languages plus auto detection. English (en) is always listed first in pickers. Codes are ISO 639-1 and validated server-side — arbitrary locale strings are rejected. Summary: en, de, it, nl, fr, es, pt, pl, ru, uk, tr, sw, ha, yo, am, zu, … (33 total)

Region	Code	Language
Detection	auto	Detect automatically
English	en	English
Europe	de	German
	it	Italian
	nl	Dutch
	fr	French
	es	Spanish
	pt	Portuguese
	pl	Polish
	ru	Russian
	uk	Ukrainian
	tr	Turkish
Africa	sw	Swahili
	ha	Hausa
	yo	Yoruba
	am	Amharic
	zu	Zulu
	xh	Xhosa
	af	Afrikaans
	tw	Twi
	ig	Igbo
Middle East	ar	Arabic
	ur	Urdu
South Asia	hi	Hindi
	bn	Bengali
	ta	Tamil
	te	Telugu
East Asia	zh	Chinese (Mandarin)
	ja	Japanese
	ko	Korean
Southeast Asia	id	Indonesian
	vi	Vietnamese
	th	Thai
	ms	Malay

GET /api/v1/stt

Lists allowlisted languages and upload caps. No auth required for the language catalog.

Multipart upload

curl -X POST http://127.0.0.1:3000/api/v1/stt \
  -H "Authorization: Bearer sk_live_…" \
  -F "audio=@clip.wav" \
  -F "language=auto"

Studio UI: /app/stt. Dubbing reuses this recognizer: Dubbing API.