AssemblyAI Universal-3.5 Pro·续

</details>

Parameters

audio_url

stringrequiredThe URL of the audio or video file to transcribe, or a data URI.

audio_start_from

integerminimum: 0maximum: 9007199254740991Timestamp in milliseconds at which to begin transcription.

audio_end_at

integerminimum: 0maximum: 9007199254740991Timestamp in milliseconds at which to stop transcription.

language_code

stringLanguage code of the audio.

language_detection

booleanWhether to automatically detect the language.

▶language_detection_options{}

object

prompt

stringNatural-language instructions for transcription style.

▶keyterms_prompt[]

arrayWords or phrases to prioritize during transcription.

temperature

numberminimum: 0maximum: 1Controls transcription randomness from 0 to 1.

punctuate

booleanWhether to add punctuation.

format_text

booleanWhether to apply text formatting.

disfluencies

booleanWhether to include filler words such as um and uh.

filter_profanity

booleanWhether to filter profanity.

speaker_labels

booleanWhether to identify speakers in the transcript.

speakers_expected

integerexclusiveMinimum: 0maximum: 9007199254740991Expected number of speakers.

▶speaker_options{}

object

multichannel

booleanWhether to transcribe each audio channel separately.

▶custom_spelling[]

array

auto_highlights

booleanWhether to extract key phrases.

content_safety

booleanWhether to detect sensitive content.

content_safety_confidence

integerminimum: 25maximum: 100Content safety confidence threshold from 25 to 100.

iab_categories

booleanWhether to classify topics using IAB categories.

entity_detection

booleanWhether to detect named entities.

sentiment_analysis

booleanWhether to analyze sentence sentiment.

domain

stringconst: medical-v1Domain-specific model for medical terminology.

speech_threshold

numberminimum: 0maximum: 1Minimum fraction of speech required for transcription.

redact_pii

booleanWhether to redact personally identifiable information.

redact_pii_audio

booleanWhether to generate an audio file with spoken PII redacted.

redact_pii_audio_quality

stringenum: mp3, wavFormat of the redacted audio file.

▶redact_pii_audio_options{}

object

▶redact_pii_policies[]

arrayPII categories to redact.

redact_pii_sub

stringenum: entity_name, hashReplacement strategy for redacted PII.

redact_pii_return_unredacted

booleanWhether to include unredacted fields alongside the redacted transcript.

▶redact_static_entities{}

objectUser-defined terms to redact, grouped by label.

text

stringThe transcribed text.

words

array | nullWord-level timestamps and confidence scores.

utterances

array | nullSpeaker-separated utterances (when speaker_labels is enabled).

confidence

numberOverall confidence score for the transcription.

language_code

stringDetected or specified language code.

language_confidence

numberConfidence score for language detection.

API Schemas (Raw)

Input Open Download

Output Open Download

Was this helpful?

YesNo

On this page

Docs

{"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/assemblyai/universal-3.5-pro/#page","headline":"AssemblyAI Universal-3.5 Pro","description":"AssemblyAI's Universal-3.5 Pro speech recognition model for fast, high-accuracy transcription.","url":"https://developers.cloudflare.com/ai/models/assemblyai/universal-3.5-pro/","inLanguage":"en","image":"https://developers.cloudflare.com/og-docs.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}}

description: FLUX.1 Kontext [max] is Black Forest Labs' highest-quality Kontext model for text-to-image generation and context-aware image editing. title: FLUX.1 Kontext [max] image: https://developers.cloudflare.com/og-docs.png

Skip to content

Documentation Index
Fetch the complete documentation index at: https://developers.cloudflare.com/llms.txt
Use this file to discover all available pages before exploring further.