All models

Universal 3 5 Pro

assemblyai/universal-3.5-pro

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "assemblyai/universal-3.5-pro",
    "audio_url": "https://example.com/input.mp3"
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "assemblyai/universal-3.5-pro", "audio_url": "https://example.com/input.mp3"}'

Parameters

Input
audio_url string required

The URL of the audio or video file to transcribe, or a data URI. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.

audio_end_at integer optional

Timestamp in milliseconds at which to stop transcription.

audio_start_from integer optional

Timestamp in milliseconds at which to begin transcription.

auto_highlights boolean optional

Whether to extract key phrases.

content_safety boolean optional

Whether to detect sensitive content.

content_safety_confidence integer optional

Content safety confidence threshold from 25 to 100.

custom_spelling array optional
disfluencies boolean optional

Whether to include filler words such as um and uh.

domain string optional

Domain-specific model for medical terminology.

entity_detection boolean optional

Whether to detect named entities.

filter_profanity boolean optional

Whether to filter profanity.

format_text boolean optional

Whether to apply text formatting.

iab_categories boolean optional

Whether to classify topics using IAB categories.

keyterms_prompt array optional

Words or phrases to prioritize during transcription.

language_code string optional

Language code of the audio.

language_detection boolean optional

Whether to automatically detect the language.

language_detection_options object optional
multichannel boolean optional

Whether to transcribe each audio channel separately.

prompt string optional

Natural-language instructions for transcription style.

punctuate boolean optional

Whether to add punctuation.

redact_pii boolean optional

Whether to redact personally identifiable information.

redact_pii_audio boolean optional

Whether to generate an audio file with spoken PII redacted.

redact_pii_audio_options object optional
redact_pii_audio_quality string optional

Format of the redacted audio file.

redact_pii_policies array optional

PII categories to redact.

redact_pii_return_unredacted boolean optional

Whether to include unredacted fields alongside the redacted transcript.

redact_pii_sub string optional

Replacement strategy for redacted PII.

redact_static_entities object optional

User-defined terms to redact, grouped by label.

sentiment_analysis boolean optional

Whether to analyze sentence sentiment.

speaker_labels boolean optional

Whether to identify speakers in the transcript.

speaker_options object optional
speakers_expected integer optional

Expected number of speakers.

speech_threshold number optional

Minimum fraction of speech required for transcription.

temperature number optional

Controls transcription randomness from 0 to 1.

Output