alibaba/fun-asr

ドキュメント
スキーマ

[Core Function] Fun-ASR transcribes a single public audio file asynchronously. [Strengths] Hot-word vocabulary, optional speaker diarization, channel selection, and language hints. [Best For] Batch transcription of recordings up to 12 hours. [Limitations] Do NOT send more than one file per request. [Routing] Use Fun ASR for recorded speech recognition, including mixed-language audio with language hints.

$0.0001/sec
speech-to-text

入力

Public HTTP/HTTPS URL of the audio file (single file).
ヒント：ファイルをドラッグ＆ドロップするか、クリップボード（Ctrl/Cmd+V）またはURLから追加できます。
Sensitive word filter configuration string.
Optional hot-word vocabulary ID.
Audio track indices (0-based).
Enable speaker diarization (mono audio; recommended ≤2h).
Language hints. When multiple values are provided, only the first is used.
language_hints
Expected speaker count; only valid when diarization_enabled is true.

結果

結果はまだありません

モデルを実行すると、ここで出力をプレビューできます。

次の操作：

README

属性

シリーズ

パラメーター

名前 説明 型 必須 列挙値
file_url Public HTTP/HTTPS URL of the audio file (single file). string はい -
special_word_filter Sensitive word filter configuration string. string いいえ -
vocabulary_id Optional hot-word vocabulary ID. string いいえ -
channel_id Audio track indices (0-based). integer[] いいえ -
diarization_enabled Enable speaker diarization (mono audio; recommended ≤2h). boolean いいえ true, false
language_hints Language hints. When multiple values are provided, only the first is used. string[] いいえ zh, en, ja, ko, vi, th, id, ms, tl, hi, ar, fr, de, es, pt, ru, it, nl, sv, da, fi, no, el, pl, cs, hu, ro, bg, hr, sk
speaker_count Expected speaker count; only valid when diarization_enabled is true. integer いいえ -

料金

入力画像（$/img）: 0.0000
入力動画（$/sec）: 0.0000

単位: $/sec

料金
$0.0001/sec

関連リソース

Fun
Funシリーズ