AssemblyAI : Universal-2

Name: Universal-2
Author: AssemblyAI

assemblyai/universal-2

actif stt 1 fournisseur

Playground

AssemblyAI high-accuracy, low-latency asynchronous transcription model with broad 99-language coverage.

AuteurAssemblyAI

Languesmultilingual

Statutactif

Démarrage rapide

Universal-2

Créez une clé API

Inscrivez-vous sur AllModels, créez une clé API et définissez-la dans ALLMODELS_API_KEY.

Créer une clé API

Envoyez une requête

Choisissez un SDK, un mode de requête et un langage. Le modèle et la route fournisseur sont déjà renseignés.

STT en streaming avec l’ElevenLabs SDK

Diffuse l’audio du micro ou d’un fichier via la route AllModels compatible ElevenLabs.

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-2",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "assemblyai"
      ]
    }
  }
});

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

Transmettez les paramètres du fournisseur

Transmettez les préférences provider via les options de requête du SDK compatible lorsque vous voulez fixer une route sur un fournisseur.

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

Fournisseurs

Plusieurs fournisseurs peuvent héberger le même modèle. Choisissez-en un lorsque vous avez besoin d’un backend fixe, ou laissez le routage choisir parmi eux.

FournisseurSlugPar heureLatenceiModesDisponibilité

AssemblyAI 49 paramètres

assemblyai

$0,15

—

Synchrone · Lot

AssemblyAI

49 paramètres fournisseur documentés pour cette route.

Tarifs

ModeLanguePar heure

Async Toutes $0,15

+ Speaker Diarization Toutes $0,02

+ Medical Mode Toutes $0,15

+ PII Redaction Toutes $0,08

+ Entity Detection Toutes $0,08

+ Profanity Filtering Toutes $0,01

Paramètres

audio_url body · string · obligatoire

The URL of the audio or video file to transcribe.

audio_end_at body · integer · facultatif

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 · facultatif

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 · facultatif

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.

par défaut false

auto_highlights body · boolean · facultatif

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

par défaut false

content_safety body · boolean · facultatif

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

par défaut false

content_safety_confidence body · integer · facultatif

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

par défaut 50min 25max 100

custom_spelling body · array · facultatif

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 · facultatif

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

par défaut false

disfluencies body · boolean · facultatif

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.

par défaut false

domain body · string | null · facultatif

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.

par défaut null

entity_detection body · boolean · facultatif

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

par défaut false

filter_profanity body · boolean · facultatif

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

par défaut false

format_text body · boolean · facultatif

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

par défaut true

iab_categories body · boolean · facultatif

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

par défaut false

keyterms_prompt body · array · facultatif

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 · facultatif

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'.

par défaut "en_us"

language_codes body · array | null · facultatif

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 · facultatif

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.

par défaut 0min 0max 1

language_detection body · boolean · facultatif

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

par défaut false

language_detection_options body · object · facultatif

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

multichannel body · boolean · facultatif

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

par défaut false

prompt body · string · facultatif

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 · facultatif

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

par défaut true

redact_pii body · boolean · facultatif

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.

par défaut false

redact_pii_audio body · boolean · facultatif

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.

par défaut false

redact_pii_audio_options body · object · facultatif

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

redact_pii_audio_quality body · string · facultatif

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 valeurs d’énumération

Valeurs

mp3wav

redact_pii_policies body · array · facultatif

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 · facultatif

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.

par défaut false

redact_pii_sub body · string | null · facultatif

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.

par défaut "hash"2 valeurs d’énumération

Valeurs

entity_namehash

redact_static_entities body · object · facultatif

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 · facultatif

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.

par défaut null2 valeurs d’énumération

Valeurs

allspeaker

sentiment_analysis body · boolean · facultatif

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

par défaut false

speaker_labels body · boolean · facultatif

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

par défaut false

speaker_options body · object · facultatif

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 · facultatif

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.

par défaut null

speech_model body · string | null · facultatif

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 · facultatif

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.

par défaut ["universal-3-pro","universal-2"]

speech_threshold body · number | null · facultatif

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.

par défaut 0min 0max 1

speech_understanding body · object · facultatif

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 · facultatif

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.

par défaut false

summary_model body · string · facultatif

The model to summarize the transcript

3 valeurs d’énumération

Valeurs

informativeconversationalcatchy

summary_type body · string · facultatif

The type of summary

5 valeurs d’énumération

Valeurs

bulletsbullets_verbosegistheadlineparagraph

temperature body · number · facultatif

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.

par défaut 0min 0max 1

topics body · array · facultatif

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

webhook_auth_header_name body · string | null · facultatif

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

par défaut null

webhook_auth_header_value body · string | null · facultatif

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

par défaut null

webhook_url body · string · facultatif

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

Langues prises en charge

Aucune liste de langues vérifiée pour ce modèle pour le moment.

Fonctionnalités

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

Supports 99 languages.

multilingual_transcription

Speaker diarization

Identifies and labels multiple speakers.

speaker_diarization

Word-level timestamps

Returns word-level timestamps.

word_timestamps

Code

STT en streaming avec l’ElevenLabs SDK

Diffuse l’audio du micro ou d’un fichier via la route AllModels compatible ElevenLabs.

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-2",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "assemblyai"
      ]
    }
  }
});

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