AssemblyAI: Universal-2

Name: Universal-2
Author: AssemblyAI

assemblyai/universal-2

activo stt 1 proveedor

Playground

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

AutorAssemblyAI

Idiomasmultilingual

Estadoactivo

Inicio rápido

Universal-2

Crea una clave API

Regístrate en AllModels, crea una clave API y guárdala como ALLMODELS_API_KEY.

Crear clave API

Haz una solicitud

Elige un SDK, un modo de solicitud y un lenguaje. El modelo y la ruta del proveedor ya están completados.

STT en streaming con el ElevenLabs SDK

Transmite audio del micrófono o de un archivo a través de la ruta de AllModels compatible con 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.

Pasa parámetros del proveedor

Pasa las preferencias de provider mediante las opciones de solicitud del SDK compatible cuando quieras fijar una ruta a un proveedor.

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

Proveedores

Distintos proveedores pueden alojar el mismo modelo. Elige un proveedor cuando necesites un backend fijo, o deja que el enrutamiento elija entre ellos.

ProveedorSlugPor horaLatenciaiModosDisponibilidad

AssemblyAI 49 parámetros

assemblyai

$0,15

—

Síncrono · Lote

AssemblyAI

49 parámetros de proveedor documentados para esta ruta.

Precios

ModoIdiomaPor hora

Async Cualquiera $0,15

+ Speaker Diarization Cualquiera $0,02

+ Medical Mode Cualquiera $0,15

+ PII Redaction Cualquiera $0,08

+ Entity Detection Cualquiera $0,08

+ Profanity Filtering Cualquiera $0,01

Parámetros

audio_url body · string · obligatorio

The URL of the audio or video file to transcribe.

audio_end_at body · integer · opcional

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 · opcional

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 · opcional

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.

predeterminado false

auto_highlights body · boolean · opcional

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

predeterminado false

content_safety body · boolean · opcional

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

predeterminado false

content_safety_confidence body · integer · opcional

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

predeterminado 50mín. 25máx. 100

custom_spelling body · array · opcional

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 · opcional

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

predeterminado false

disfluencies body · boolean · opcional

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.

predeterminado false

domain body · string | null · opcional

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.

predeterminado null

entity_detection body · boolean · opcional

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

predeterminado false

filter_profanity body · boolean · opcional

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

predeterminado false

format_text body · boolean · opcional

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

predeterminado true

iab_categories body · boolean · opcional

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

predeterminado false

keyterms_prompt body · array · opcional

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 · opcional

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'.

predeterminado "en_us"

language_codes body · array | null · opcional

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 · opcional

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.

predeterminado 0mín. 0máx. 1

language_detection body · boolean · opcional

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

predeterminado false

language_detection_options body · object · opcional

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

multichannel body · boolean · opcional

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

predeterminado false

prompt body · string · opcional

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 · opcional

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

predeterminado true

redact_pii body · boolean · opcional

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.

predeterminado false

redact_pii_audio body · boolean · opcional

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.

predeterminado false

redact_pii_audio_options body · object · opcional

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

redact_pii_audio_quality body · string · opcional

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 valores enum

Valores

mp3wav

redact_pii_policies body · array · opcional

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 · opcional

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.

predeterminado false

redact_pii_sub body · string | null · opcional

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.

predeterminado "hash"2 valores enum

Valores

entity_namehash

redact_static_entities body · object · opcional

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 · opcional

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.

predeterminado null2 valores enum

Valores

allspeaker

sentiment_analysis body · boolean · opcional

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

predeterminado false

speaker_labels body · boolean · opcional

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

predeterminado false

speaker_options body · object · opcional

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 · opcional

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.

predeterminado null

speech_model body · string | null · opcional

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 · opcional

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.

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

speech_threshold body · number | null · opcional

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.

predeterminado 0mín. 0máx. 1

speech_understanding body · object · opcional

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 · opcional

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.

predeterminado false

summary_model body · string · opcional

The model to summarize the transcript

3 valores enum

Valores

informativeconversationalcatchy

summary_type body · string · opcional

The type of summary

5 valores enum

Valores

bulletsbullets_verbosegistheadlineparagraph

temperature body · number · opcional

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.

predeterminado 0mín. 0máx. 1

topics body · array · opcional

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

webhook_auth_header_name body · string | null · opcional

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

predeterminado null

webhook_auth_header_value body · string | null · opcional

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

predeterminado null

webhook_url body · string · opcional

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

Idiomas admitidos

Todavía no hay una lista de idiomas revisada para este modelo.

Funciones

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

Código

STT en streaming con el ElevenLabs SDK

Transmite audio del micrófono o de un archivo a través de la ruta de AllModels compatible con 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.