AssemblyAI: Universal-3.5 Pro

Name: Universal-3.5 Pro
Author: AssemblyAI

assemblyai/universal-3-5-pro

提供中 stt 1プロバイダー

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).

作成者AssemblyAI

言語18言語

ステータス提供中

クイックスタート

Universal-3.5 Pro

APIキーを作成する

AllModelsに登録してAPIキーを作成し、ALLMODELS_API_KEYとして設定します。

APIキーを作成

リクエストを送る

SDK、リクエストモード、言語を選びます。モデルとプロバイダールートは入力済みです。

ElevenLabs SDKでのストリーミングSTT

マイクまたはファイルの音声を、ElevenLabs互換のAllModelsルート経由でストリーミングします。

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.

プロバイダーパラメーターを渡す

ルートを特定のプロバイダーに固定したい場合は、互換SDKのリクエストオプションでproviderの設定を渡します。

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

プロバイダー

同じモデルを複数のプロバイダーがホストしている場合があります。バックエンドを固定したい場合は1つのプロバイダーを選び、そうでなければルーティングに選択を任せられます。

プロバイダーSlug1時間あたりレイテンシiモード稼働率

AssemblyAI 49個のパラメーター

assemblyai

$0.21

—

同期 · バッチ

AssemblyAI

このルートには49個のプロバイダーパラメーターが記載されています。

料金

モード言語1時間あたり

Async すべて $0.21

+ Speaker Diarization すべて $0.02

+ Medical Mode すべて $0.15

+ PII Redaction すべて $0.08

+ Entity Detection すべて $0.08

+ Profanity Filtering すべて $0.01

パラメーター

audio_url body · string · 必須

The URL of the audio or video file to transcribe.

audio_end_at body · integer · 任意

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 · 任意

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 · 任意

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.

デフォルト false

auto_highlights body · boolean · 任意

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

デフォルト false

content_safety body · boolean · 任意

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

デフォルト false

content_safety_confidence body · integer · 任意

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

デフォルト 50最小 25最大 100

custom_spelling body · array · 任意

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 · 任意

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

デフォルト false

disfluencies body · boolean · 任意

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.

デフォルト false

domain body · string | null · 任意

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.

デフォルト null

entity_detection body · boolean · 任意

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

デフォルト false

filter_profanity body · boolean · 任意

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

デフォルト false

format_text body · boolean · 任意

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

デフォルト true

iab_categories body · boolean · 任意

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

デフォルト false

keyterms_prompt body · array · 任意

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 · 任意

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'.

デフォルト "en_us"

language_codes body · array | null · 任意

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 · 任意

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.

デフォルト 0最小 0最大 1

language_detection body · boolean · 任意

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

デフォルト false

language_detection_options body · object · 任意

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

multichannel body · boolean · 任意

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

デフォルト false

prompt body · string · 任意

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 · 任意

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

デフォルト true

redact_pii body · boolean · 任意

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.

デフォルト false

redact_pii_audio body · boolean · 任意

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.

デフォルト false

redact_pii_audio_options body · object · 任意

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

redact_pii_audio_quality body · string · 任意

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個の列挙値

値

mp3wav

redact_pii_policies body · array · 任意

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 · 任意

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.

デフォルト false

redact_pii_sub body · string | null · 任意

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.

デフォルト "hash"2個の列挙値

値

entity_namehash

redact_static_entities body · object · 任意

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 · 任意

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.

デフォルト null2個の列挙値

値

allspeaker

sentiment_analysis body · boolean · 任意

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

デフォルト false

speaker_labels body · boolean · 任意

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

デフォルト false

speaker_options body · object · 任意

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 · 任意

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.

デフォルト null

speech_model body · string | null · 任意

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 · 任意

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.

デフォルト ["universal-3-pro","universal-2"]

speech_threshold body · number | null · 任意

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.

デフォルト 0最小 0最大 1

speech_understanding body · object · 任意

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 · 任意

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.

デフォルト false

summary_model body · string · 任意

The model to summarize the transcript

3個の列挙値

値

informativeconversationalcatchy

summary_type body · string · 任意

The type of summary

5個の列挙値

値

bulletsbullets_verbosegistheadlineparagraph

temperature body · number · 任意

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.

デフォルト 0最小 0最大 1

topics body · array · 任意

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

webhook_auth_header_name body · string | null · 任意

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

デフォルト null

webhook_auth_header_value body · string | null · 任意

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

デフォルト null

webhook_url body · string · 任意

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

対応言語

18言語

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

機能

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

コード

ElevenLabs SDKでのストリーミングSTT

マイクまたはファイルの音声を、ElevenLabs互換のAllModelsルート経由でストリーミングします。

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.