Whisper-1

Whisper is a general-purpose speech recognition model trained on a large and diverse audio dataset. It can also be used as a multitask model for multilingual speech recognition, speech translation, and language identification.

能力

"POST", "endpoint": "/v1/audio/transcriptions", "protocol": "audio-stt", "parameters": {"optional": {"language": {"type": "string"}, "response_format": {"type": "string", "default": "json"}}, "required": ["model", "file"]}, "validation": {"timeout_ms": 60000, "status_codes": [200], "response_path": "text", "must_be_non_empty": false}, "test_request": {"_note": "Requires multipart/form-data upload with audio file", "model": "{{model}}"}}

输入

text

输出

text

区域

global

验证时间

2026-08-15T04:50:43.134798981+00:00

价格

180 IFT / 1M tokens

文档

-

调用示例

curl https://api.inferlink.ai/v1/chat/completions \
  -H 'Authorization: Bearer $INFERLINK_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model":"inferlink/inferlink/whisper-1","messages":[{"role":"user","content":"Hello"}]}'