Create transcription
音訊
建立轉錄
Transcribe uploaded audio into text with the OpenAI-compatible Whisper-style interface. Supported formats: FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, and WebM.
POST
Create transcription
授權
Your DGrid API key. All endpoints use Authorization: Bearer <DGRID_API_KEY>.
主體
multipart/form-data
Audio file up to 25 MB.
Model ID, such as whisper-1.
ISO-639-1 language code, such as en, zh, or ko.
Optional prompt for biasing the transcript.
可用選項:
json, text, srt, verbose_json, vtt Sampling temperature.
必填範圍:
0 <= x <= 1回應
Transcript. When response_format is verbose_json, the response also includes task, language, duration, and per-segment timing metadata.
Transcript text.

