Skip to content

非公式本サイトは非公式の日本語ドキュメントであり、Cloudflare 公式サイトではありません。最新情報はdevelopers.cloudflare.comをご確認ください。

AssemblyAI のロゴ

AssemblyAI Universal-3.5 Pro

音声認識 • AssemblyAI

Markdown で表示Agent セットアップ
  • サードパーティ

AssemblyAI の Universal-3.5 Pro は、高速かつ高精度な文字起こし向けの音声認識モデルです。

モデル情報
利用規約とライセンスリンク
詳細情報リンク
料金Cloudflare ダッシュボードで料金を見る

使い方

const response = await env.AI.run(
  'assemblyai/universal-3.5-pro',
  { audio_url: 'https://cdn.openai.com/API/docs/audio/alloy.wav' },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "assemblyai/universal-3.5-pro",
  "input": {
    "audio_url": "https://cdn.openai.com/API/docs/audio/alloy.wav"
  }
}'
The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years.
{
  "id": "93b8082d-22c2-4dd0-adf6-0037d2c7027a",
  "language_model": "assemblyai_default",
  "acoustic_model": "assemblyai_default",
  "language_code": "en",
  "speech_understanding": null,
  "translated_texts": null,
  "status": "completed",
  "audio_url": "https://cdn.openai.com/API/docs/audio/alloy.wav",
  "text": "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years.",
  "words": [
    {
      "text": "The",
      "start": 32,
      "end": 129,
      "confidence": 0.95348084,
      "speaker": null
    },
    {
      "text": "sun",
      "start": 129,
      "end": 404,
      "confidence": 0.97099674,
      "speaker": null
    },
    {
      "text": "rises",
      "start": 420,
      "end": 809,
      "confidence": 0.9999746,
      "speaker": null
    },
    {
      "text": "in",
      "start": 841,
      "end": 922,
      "confidence": 0.999997,
      "speaker": null
    },
    {
      "text": "the",
      "start": 922,
      "end": 1068,
      "confidence": 0.99999905,
      "speaker": null
    },
    {
      "text": "east",
      "start": 1149,
      "end": 1456,
      "confidence": 0.9853527,
      "speaker": null
    },
    {
      "text": "and",
      "start": 1570,
      "end": 1634,
      "confidence": 0.999203,
      "speaker": null
    },
    {
      "text": "sets",
      "start": 1715,
      "end": 2055,
      "confidence": 0.999995,
      "speaker": null
    },
    {
      "text": "in",
      "start": 2055,
      "end": 2104,
      "confidence": 0.99999857,
      "speaker": null
    },
    {
      "text": "the",
      "start": 2120,
      "end": 2217,
      "confidence": 0.9999993,
      "speaker": null
    },
    {
      "text": "west.",
      "start": 2217,
      "end": 2638,
      "confidence": 0.9959912,
      "speaker": null
    },
    {
      "text": "This",
      "start": 3107,
      "end": 3221,
      "confidence": 0.9999709,
      "speaker": null
    },
    {
      "text": "simple",
      "start": 3269,
      "end": 3560,
      "confidence": 0.9999976,
      "speaker": null
    },
    {
      "text": "fact",
      "start": 3593,
      "end": 3997,
      "confidence": 0.999998,
      "speaker": null
    },
    {
      "text": "has",
      "start": 3997,
      "end": 4175,
      "confidence": 0.999995,
      "speaker": null
    },
    {
      "text": "been",
      "start": 4224,
      "end": 4289,
      "confidence": 0.9999974,
      "speaker": null
    },
    {
      "text": "observed",
      "start": 4337,
      "end": 4807,
      "confidence": 0.9999957,
      "speaker": null
    },
    {
      "text": "by",
      "start": 4807,
      "end": 4952,
      "confidence": 0.999998,
      "speaker": null
    },
    {
      "text": "humans",
      "start": 4969,
      "end": 5422,
      "confidence": 0.99999607,
      "speaker": null
    },
    {
      "text": "for",
      "start": 5422,
      "end": 5519,
      "confidence": 0.99999416,
      "speaker": null
    },
    {
      "text": "thousands",
      "start": 5616,
      "end": 6118,
      "confidence": 0.9999938,
      "speaker": null
    },
    {
      "text": "of",
      "start": 6118,
      "end": 6231,
      "confidence": 0.9999945,
      "speaker": null
    },
    {
      "text": "years.",
      "start": 6328,
      "end": 6636,
      "confidence": 0.9984148,
      "speaker": null
    }
  ],
  "utterances": null,
  "confidence": 0.9957971,
  "audio_duration": 7,
  "punctuate": true,
  "format_text": true,
  "webhook_url": null,
  "webhook_status_code": null,
  "webhook_auth": false,
  "webhook_auth_header_name": null,
  "speed_boost": false,
  "auto_highlights_result": null,
  "auto_highlights": false,
  "audio_start_from": null,
  "audio_end_at": null,
  "word_boost": [],
  "boost_param": null,
  "prompt": null,
  "keyterms_prompt": [],
  "filter_profanity": false,
  "redact_pii": false,
  "redact_pii_audio": false,
  "redact_pii_audio_quality": null,
  "redact_pii_audio_options": null,
  "redact_pii_policies": null,
  "redact_pii_sub": null,
  "redact_static_entities": null,
  "speaker_labels": false,
  "speaker_options": null,
  "content_safety": false,
  "iab_categories": false,
  "content_safety_labels": {
    "status": "unavailable",
    "results": [],
    "summary": {}
  },
  "iab_categories_result": {
    "status": "unavailable",
    "results": [],
    "summary": {}
  },
  "language_detection": true,
  "language_detection_options": null,
  "language_detection_results": null,
  "language_confidence_threshold": null,
  "language_confidence": 0.9998,
  "custom_spelling": null,
  "throttled": false,
  "auto_chapters": false,
  "summarization": false,
  "summary_type": null,
  "summary_model": null,
  "custom_topics": false,
  "topics": [],
  "speech_threshold": null,
  "speech_model": null,
  "speech_models": [
    "universal-3-5-pro"
  ],
  "speech_model_used": "universal-3-5-pro",
  "temperature": null,
  "remove_audio_tags": "all",
  "chapters": null,
  "disfluencies": false,
  "entity_detection": false,
  "sentiment_analysis": false,
  "sentiment_analysis_results": null,
  "entities": null,
  "speakers_expected": null,
  "summary": null,
  "custom_topics_results": null,
  "is_deleted": null,
  "multichannel": null,
  "project_id": 1747096,
  "token_id": 1768830
}

言語とキーワード — 明示した言語と分野用語で文字起こしします
const response = await env.AI.run(
  'assemblyai/universal-3.5-pro',
  {
    audio_url: 'https://cdn.openai.com/API/docs/audio/echo.wav',
    language_code: 'en',
    keyterms_prompt: ['Kubernetes', 'microservices', 'containerization', 'load balancer'],
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "assemblyai/universal-3.5-pro",
  "input": {
    "audio_url": "https://cdn.openai.com/API/docs/audio/echo.wav",
    "language_code": "en",
    "keyterms_prompt": [
      "Kubernetes",
      "microservices",
      "containerization",
      "load balancer"
    ]
  }
}'
In the heart of the city, there is a large park where people go to relax and enjoy nature. The park has a beautiful pond with ducks and swans.
{
  "id": "7f184aba-4a6d-49fa-b47a-f2ec47e67878",
  "language_model": "assemblyai_default",
  "acoustic_model": "assemblyai_default",
  "language_code": "en_us",
  "speech_understanding": null,
  "translated_texts": null,
  "status": "completed",
  "audio_url": "https://cdn.openai.com/API/docs/audio/echo.wav",
  "text": "In the heart of the city, there is a large park where people go to relax and enjoy nature. The park has a beautiful pond with ducks and swans.",
  "words": [
    {
      "text": "In",
      "start": 32,
      "end": 80,
      "confidence": 0.99823916,
      "speaker": null
    },
    {
      "text": "the",
      "start": 177,
      "end": 241,
      "confidence": 0.9997907,
      "speaker": null
    },
    {
      "text": "heart",
      "start": 258,
      "end": 500,
      "confidence": 0.9998222,
      "speaker": null
    },
    {
      "text": "of",
      "start": 500,
      "end": 548,
      "confidence": 0.9999982,
      "speaker": null
    },
    {
      "text": "the",
      "start": 596,
      "end": 677,
      "confidence": 0.99993014,
      "speaker": null
    },
    {
      "text": "city,",
      "start": 677,
      "end": 967,
      "confidence": 0.9999535,
      "speaker": null
    },
    {
      "text": "there",
      "start": 1322,
      "end": 1435,
      "confidence": 0.99998367,
      "speaker": null
    },
    {
      "text": "is",
      "start": 1467,
      "end": 1516,
      "confidence": 0.9989073,
      "speaker": null
    },
    {
      "text": "a",
      "start": 1564,
      "end": 1596,
      "confidence": 0.99998987,
      "speaker": null
    },
    {
      "text": "large",
      "start": 1709,
      "end": 2016,
      "confidence": 0.99996316,
      "speaker": null
    },
    {
      "text": "park",
      "start": 2129,
      "end": 2467,
      "confidence": 0.99998546,
      "speaker": null
    },
    {
      "text": "where",
      "start": 2693,
      "end": 2838,
      "confidence": 0.99389255,
      "speaker": null
    },
    {
      "text": "people",
      "start": 2854,
      "end": 3145,
      "confidence": 0.99998343,
      "speaker": null
    },
    {
      "text": "go",
      "start": 3177,
      "end": 3338,
      "confidence": 0.9999392,
      "speaker": null
    },
    {
      "text": "to",
      "start": 3338,
      "end": 3467,
      "confidence": 0.9999963,
      "speaker": null
    },
    {
      "text": "relax",
      "start": 3500,
      "end": 4064,
      "confidence": 0.99998176,
      "speaker": null
    },
    {
      "text": "and",
      "start": 4064,
      "end": 4161,
      "confidence": 0.99998665,
      "speaker": null
    },
    {
      "text": "enjoy",
      "start": 4161,
      "end": 4484,
      "confidence": 0.9999976,
      "speaker": null
    },
    {
      "text": "nature.",
      "start": 4484,
      "end": 4887,
      "confidence": 0.9999689,
      "speaker": null
    },
    {
      "text": "The",
      "start": 5597,
      "end": 5758,
      "confidence": 0.9997563,
      "speaker": null
    },
    {
      "text": "park",
      "start": 5758,
      "end": 6016,
      "confidence": 0.99999034,
      "speaker": null
    },
    {
      "text": "has",
      "start": 6064,
      "end": 6177,
      "confidence": 0.99998844,
      "speaker": null
    },
    {
      "text": "a",
      "start": 6177,
      "end": 6242,
      "confidence": 0.9999819,
      "speaker": null
    },
    {
      "text": "beautiful",
      "start": 6322,
      "end": 6774,
      "confidence": 0.9999924,
      "speaker": null
    },
    {
      "text": "pond",
      "start": 6790,
      "end": 7193,
      "confidence": 0.99999106,
      "speaker": null
    },
    {
      "text": "with",
      "start": 7193,
      "end": 7355,
      "confidence": 0.9997123,
      "speaker": null
    },
    {
      "text": "ducks",
      "start": 7371,
      "end": 7806,
      "confidence": 0.9999808,
      "speaker": null
    },
    {
      "text": "and",
      "start": 7855,
      "end": 7919,
      "confidence": 0.9999771,
      "speaker": null
    },
    {
      "text": "swans.",
      "start": 7935,
      "end": 8629,
      "confidence": 0.99828225,
      "speaker": null
    }
  ],
  "utterances": null,
  "confidence": 0.9995849,
  "audio_duration": 9,
  "punctuate": true,
  "format_text": true,
  "webhook_url": null,
  "webhook_status_code": null,
  "webhook_auth": false,
  "webhook_auth_header_name": null,
  "speed_boost": false,
  "auto_highlights_result": null,
  "auto_highlights": false,
  "audio_start_from": null,
  "audio_end_at": null,
  "word_boost": [],
  "boost_param": null,
  "prompt": null,
  "keyterms_prompt": [
    "Kubernetes",
    "microservices",
    "containerization",
    "load balancer"
  ],
  "filter_profanity": false,
  "redact_pii": false,
  "redact_pii_audio": false,
  "redact_pii_audio_quality": null,
  "redact_pii_audio_options": null,
  "redact_pii_policies": null,
  "redact_pii_sub": null,
  "redact_static_entities": null,
  "speaker_labels": false,
  "speaker_options": null,
  "content_safety": false,
  "iab_categories": false,
  "content_safety_labels": {
    "status": "unavailable",
    "results": [],
    "summary": {}
  },
  "iab_categories_result": {
    "status": "unavailable",
    "results": [],
    "summary": {}
  },
  "language_detection": false,
  "language_detection_options": null,
  "language_detection_results": null,
  "language_confidence_threshold": null,
  "language_confidence": null,
  "custom_spelling": null,
  "throttled": false,
  "auto_chapters": false,
  "summarization": false,
  "summary_type": null,
  "summary_model": null,
  "custom_topics": false,
  "topics": [],
  "speech_threshold": null,
  "speech_model": null,
  "speech_models": [
    "universal-3-5-pro"
  ],
  "speech_model_used": "universal-3-5-pro",
  "temperature": null,
  "remove_audio_tags": "all",
  "chapters": null,
  "disfluencies": false,
  "entity_detection": false,
  "sentiment_analysis": false,
  "sentiment_analysis_results": null,
  "entities": null,
  "speakers_expected": null,
  "summary": null,
  "custom_topics_results": null,
  "is_deleted": null,
  "multichannel": null,
  "project_id": 1747096,
  "token_id": 1768830
}

パラメーター

audio_url
string必須書き起こす音声または動画ファイルの URL、または data URI です。
audio_start_from
integerminimum: 0maximum: 9007199254740991書き起こしを開始するミリ秒のタイムスタンプです。
audio_end_at
integerminimum: 0maximum: 9007199254740991書き起こしを終了するミリ秒のタイムスタンプです。
language_code
string音声の言語コードです。
language_detection
boolean言語を自動検出するかどうかです。
prompt
string書き起こしスタイル向けの自然言語の指示です。
temperature
numberminimum: 0maximum: 1書き起こしのランダムさを 0 から 1 で制御します。
punctuate
boolean句読点を付けるかどうかです。
format_text
booleanテキストの書式を適用するかどうかです。
disfluencies
boolean`um` や `uh` などのフィラー語を含めるかどうかです。
filter_profanity
boolean不適切な表現を除くかどうかです。
speaker_labels
boolean書き起こしで話者を識別するかどうかです。
speakers_expected
integerexclusiveMinimum: 0maximum: 9007199254740991想定する話者数です。
multichannel
boolean各音声チャンネルを個別に書き起こすかどうかです。
auto_highlights
booleanキーフレーズを抽出するかどうかです。
content_safety
booleanセンシティブな内容を検出するかどうかです。
content_safety_confidence
integerminimum: 25maximum: 100コンテンツセーフティの信頼度しきい値です(25〜100)。
iab_categories
booleanIAB カテゴリでトピックを分類するかどうかです。
entity_detection
boolean固有表現を検出するかどうかです。
sentiment_analysis
boolean文の感情を分析するかどうかです。
domain
stringconst: medical-v1医療用語向けのドメイン固有モデルです。
speech_threshold
numberminimum: 0maximum: 1書き起こしに必要な音声の最小割合です。
redact_pii
boolean個人を特定できる情報をマスキングするかどうかです。
redact_pii_audio
boolean発話された PII をマスキングした音声ファイルを生成するかどうかです。
redact_pii_audio_quality
stringenum: mp3, wavマスキング済み音声ファイルの形式です。
redact_pii_sub
stringenum: entity_name, hashマスキングした PII の置換方法です。
redact_pii_return_unredacted
booleanマスキング済みの書き起こしと一緒に、マスキング前のフィールドも含めるかどうかです。
text
string書き起こしたテキストです。
words
array | null単語単位のタイムスタンプと信頼度スコアです。
utterances
array | null話者ごとに分けた発話です(`speaker_labels` が有効なとき)。
confidence
number | null書き起こし全体の信頼度スコアです。
language_code
string | null検出または指定した言語コードです。
language_confidence
number | null言語検出の信頼度スコアです。

API スキーマ(Raw)

Input
Output

役に立ちましたか?