openai/whisper-1

ドキュメント
スキーマ

[Core Function] OpenAI Whisper transcribes a single public audio URL into text via an async task. [Strengths] Multiple output formats (verbose_json with word/segment timestamps, plain text, SRT, VTT), optional language and prompt biasing. [Best For] Meeting notes, podcasts, captions, and batch audio-to-text. [Limitations] Do NOT use file upload; URL-only input (audio up to 25 MB). Prefer verbose_json when you need duration or timestamps. [Routing] Use whisper-1 for OpenAI Whisper quality with URL-based audio.

$0.0001/sec
speech-to-text

入力

Optional text to guide the model's style or continue a previous segment.
Public http(s) URL of the audio file (max 25 MB).
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。
ISO-639-1 language hint for transcription.
Output format. verbose_json recommended for duration and timestamps.
Sampling temperature; higher values increase randomness.
Timestamp detail levels. Requires response_format=verbose_json when non-empty.
timestamp_granularities

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。

次へ：

README

属性

パラメーター

名前 説明 型 必須 列挙値
prompt Optional text to guide the model’s style or continue a previous segment. string いいえ -
url Public http(s) URL of the audio file (max 25 MB). string はい -
language ISO-639-1 language hint for transcription. string いいえ -
response_format Output format. verbose_json recommended for duration and timestamps. string いいえ json, text, srt, verbose_json, vtt
temperature Sampling temperature; higher values increase randomness. number いいえ -
timestamp_granularities Timestamp detail levels. Requires response_format=verbose_json when non-empty. string[] いいえ word, segment

料金

単位: $/sec

料金
$0.0001/sec