AssemblyAI: Universal-3.5 Pro

Name: Universal-3.5 Pro
Author: AssemblyAI

assemblyai/universal-3-5-pro

active stt 1 provider

Playground

AssemblyAI Universal-3.5 Pro pre-recorded transcription: highest-accuracy async speech recognition with 18-language support, native code switching and contextual prompting, distinct from the realtime Universal-3.5 Pro (u3-rt-pro).

AuthorAssemblyAI

Languages18 languages

Statusactive

Quick start

Universal-3.5 Pro

Create an API key

Create API key

Make a request

Pick an SDK, request mode, and language. The model and provider route are already filled in.

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "assemblyai/universal-3-5-pro",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "assemblyai"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.

Pass provider parameters

Pass provider preferences through the compatible SDK request options when you want to pin a route to a provider.

{
  queryParams: {
    provider: {
      only: ["assemblyai"]
    }
  }
}

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer hourLatencyiModesUptime

AssemblyAI 49 params

assemblyai

$0.21

—

Synchronous · Batch

AssemblyAI

49 documented provider parameters for this route.

Pricing

ModeLanguagePer hour

Async Any $0.21

+ Speaker Diarization Any $0.02

+ Medical Mode Any $0.15

+ PII Redaction Any $0.08

+ Entity Detection Any $0.08

+ Profanity Filtering Any $0.01

Parameters

audio_url body · string · required

The URL of the audio or video file to transcribe.

audio_end_at body · integer · optional

The point in time, in milliseconds, to stop transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.

audio_start_from body · integer · optional

The point in time, in milliseconds, to begin transcribing in your media file. See [Set the start and end of the transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) for more details.

auto_chapters body · boolean · optional

Enable [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters), can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible chapter summaries. See the [updated Auto Chapters page](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) for details. Note: This parameter is only supported for the Universal-2 model.

default false

auto_highlights body · boolean · optional

Enable [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases), either true or false

default false

content_safety body · boolean · optional

Enable [Content Moderation](https://www.assemblyai.com/docs/content-moderation), can be true or false

default false

content_safety_confidence body · integer · optional

The confidence threshold for the [Content Moderation](https://www.assemblyai.com/docs/content-moderation) model. Values must be between 25 and 100.

default 50min 25max 100

custom_spelling body · array · optional

Customize how words are spelled and formatted using to and from values. See [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) for more details.

custom_topics body · boolean · optional

This parameter does not currently have any functionality attached to it.

default false

disfluencies body · boolean · optional

Transcribe [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words), like "umm", in your media file; can be true or false. Supported on Universal-3 Pro and Universal-2.

default false

domain body · string | null · optional

Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `"medical-v1"` to enable [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages. Supported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If used with an unsupported language, the parameter is ignored and a warning is returned.

default null

entity_detection body · boolean · optional

Enable [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection), can be true or false

default false

filter_profanity body · boolean · optional

Filter profanity from the transcribed text, can be true or false. See [Profanity Filtering](https://www.assemblyai.com/docs/profanity-filtering) for more details.

default false

format_text body · boolean · optional

Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false

default true

iab_categories body · boolean · optional

Enable [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection), can be true or false

default false

keyterms_prompt body · array · optional

Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3 Pro) domain-specific words or phrases (maximum 6 words per phrase). See [Keyterms Prompting](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-pro/prompting#keyterms-prompting) for more details.

language_code body · string | string | null · optional

The language of your audio file. Possible values are found in [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages). The default value is 'en_us'.

default "en_us"

language_codes body · array | null · optional

The language codes of your audio file. Used for [Code switching](/speech-to-text/pre-recorded-audio/code-switching) One of the values specified must be `en`.

language_confidence_threshold body · number · optional

The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold. Defaults to 0. See [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) for more details.

default 0min 0max 1

language_detection body · boolean · optional

Enable [Automatic language detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection), either true or false.

default false

language_detection_options body · object · optional

Specify options for [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection).

multichannel body · boolean · optional

Enable [Multichannel](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) transcription, can be true or false.

default false

prompt body · string · optional

Provide natural language prompting of up to 1,500 words of contextual information to the model. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for best practices. Note: This parameter is only supported for the Universal-3 Pro model.

punctuate body · boolean · optional

Enable [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false

default true

redact_pii body · boolean · optional

Redact PII from the transcribed text using the Redact PII model, can be true or false. See [PII Redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.

default false

redact_pii_audio body · boolean · optional

Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.

default false

redact_pii_audio_options body · object · optional

Specify options for [PII redacted audio](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) files.

redact_pii_audio_quality body · string · optional

Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction#request-for-redacted-audio) for more details.

2 enum values

Values

mp3wav

redact_pii_policies body · array · optional

The list of PII Redaction policies to enable. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.

redact_pii_return_unredacted body · boolean · optional

When set to `true`, returns the original unredacted transcript alongside the redacted one in the same response. Requires `redact_pii` to be `true`, otherwise a 400 error is returned. When enabled, the response includes the additional fields `unredacted_text`, `unredacted_words`, and `unredacted_utterances`. The existing `text`, `words`, and `utterances` fields remain fully redacted. When disabled (default), the response is unchanged and contains only the redacted transcript. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.

default false

redact_pii_sub body · string | null · optional

The replacement logic for detected PII, can be `entity_type` or `hash`. See [PII redaction](https://www.assemblyai.com/docs/pii-redaction) for more details.

default "hash"2 enum values

Values

entity_namehash

redact_static_entities body · object · optional

A map of user-defined terms to redact, where each key is a redaction label and each value is a list of exact terms to match (e.g. `{ "INTERNAL_TOOL": ["Bearclaw", "Cubclaw"] }`). Each matching term in the transcript is redacted using the `redact_pii_sub` substitution, on top of standard PII Redaction. Useful for redacting specific, predefined terms (proprietary names, internal codenames) that aren't general PII categories. This is a literal find-and-replace (tolerant of casing, surrounding punctuation, and minor spacing/hyphenation), not a model — it does not generalize beyond the terms you provide. Requires `redact_pii` to be `true`, otherwise a 400 error is returned. When `redact_pii_audio` is enabled, matched terms are also redacted in the audio output. See [Static Entity Redaction](https://www.assemblyai.com/docs/guardrails/redact-pii-from-transcripts#static-entity-redaction) for more details.

remove_audio_tags body · string | null · optional

Universal-3 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. Set to `"all"` to remove all inline annotations, or `"speaker"` to remove only speaker cues while keeping other annotations. Note: This parameter is only supported for the Universal-3 Pro model.

default null2 enum values

Values

allspeaker

sentiment_analysis body · boolean · optional

Enable [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis), can be true or false

default false

speaker_labels body · boolean · optional

Enable [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers), can be true or false

default false

speaker_options body · object · optional

Specify options for [Speaker diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers). Use this to set a range of possible speakers.

speakers_expected body · integer | null · optional

Tells the speaker label model how many speakers it should attempt to identify. See [Set number of speakers expected](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-number-of-speakers-expected) for more details.

default null

speech_model body · string | null · optional

This parameter has been replaced with the `speech_models` parameter, learn more about the `speech_models` parameter [here](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model).

speech_models body · array · optional

Optional. List multiple speech models in priority order, allowing our system to automatically route your audio to the best available option. If omitted, defaults to `["universal-3-pro", "universal-2"]`. See [Model Selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) for available models and routing behavior.

default ["universal-3-pro","universal-2"]

speech_threshold body · number | null · optional

Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive. See [Speech Threshold](https://www.assemblyai.com/docs/speech-threshold) for more details.

default 0min 0max 1

speech_understanding body · object · optional

Enable speech understanding tasks like [Translation](https://www.assemblyai.com/docs/speech-understanding/translation), [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification), and [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting). See the task-specific docs for available options and configuration.

summarization body · boolean · optional

Enable [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization), can be true or false. Deprecated - use [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/quickstart) instead for more flexible summaries. See the [updated Summarization page](https://www.assemblyai.com/docs/speech-understanding/summarization) for details. Note: This parameter is only supported for the Universal-2 model.

default false

summary_model body · string · optional

The model to summarize the transcript

3 enum values

Values

informativeconversationalcatchy

summary_type body · string · optional

The type of summary

5 enum values

Values

bulletsbullets_verbosegistheadlineparagraph

temperature body · number · optional

Control the amount of randomness injected into the model's response. See the [Prompting Guide](https://www.assemblyai.com/docs/pre-recorded-audio/prompting) for more details. Note: This parameter can only be used with the Universal-3 Pro model.

default 0min 0max 1

topics body · array · optional

This parameter does not currently have any functionality attached to it.

webhook_auth_header_name body · string | null · optional

The header name to be sent with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests

default null

webhook_auth_header_value body · string | null · optional

The header value to send back with the transcript completed or failed [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests for added security

default null

webhook_url body · string · optional

The URL to which we send [webhook](https://www.assemblyai.com/docs/deployment/webhooks-for-pre-recorded-audio) requests.

Supported languages

18 languages

English en

Spanish es

German de

French fr

Portuguese pt

Italian it

Turkish tr

Dutch nl

Swedish sv

Norwegian no

Danish da

Finnish fi

Hindi hi

Vietnamese vi

Arabic ar

Hebrew he

Japanese ja

Mandarin zh

Features

Speech to text

Transcribes spoken audio to text.

speech_to_text

Synchronous

Transcribes a fully-submitted audio file in a single synchronous request.

synchronous

Batch

AssemblyAI processes the request in a queue (submit, then poll for the transcript).

batch

Multilingual transcription

Multilingual coverage.

multilingual_transcription

Speaker diarization

Identifies and labels multiple speakers.

speaker_diarization

Word-level timestamps

Returns word-level timestamps.

word_timestamps

PII redaction

Supports PII redaction (redact_pii) on pre-recorded transcripts.

pii_redaction

Code

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "assemblyai/universal-3-5-pro",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "assemblyai"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.