[openai.whisper]
openai.whisper is a slot in the openai namespace, in Hyperlambda, the language of Magic Cloud. Transcribes audio content using OpenAI Whisper.
- Returns: Resolves to the transcribed text
Arguments
Required arguments come first, then the optional ones in the order they are declared.
| Argument | Type | Required | Description |
|---|---|---|---|
[key] |
string | yes | OpenAI API key. |
[content] |
byte[] | yes | Audio content bytes. |
[type] |
string | yes | Audio MIME type. |
[language] |
string | no | Optional language hint. |
Guide: How to use [openai.whisper]
JSON declaration
This is the complete declaration of openai.whisper, as the running system describes it. It is also published as slot.json.
JSON declaration
{
"name": "openai.whisper",
"description": "Transcribes audio content using OpenAI Whisper",
"signature": {
"children": {
"key": {
"type": "string",
"kind": "openai-api-key",
"description": "OpenAI API key",
"required": true,
"mode": "ValueOrExpression",
"cardinality": "ExactlyOne",
"role": "Option",
"projection": "Value"
},
"content": {
"type": "byte[]",
"kind": "binary-content",
"description": "Audio content bytes",
"required": true,
"mode": "ValueOrExpression",
"cardinality": "ExactlyOne",
"role": "Option",
"projection": "Value"
},
"type": {
"type": "string",
"kind": "content-type",
"description": "Audio MIME type",
"required": true,
"mode": "ValueOrExpression",
"cardinality": "ExactlyOne",
"role": "Option",
"projection": "Value"
},
"language": {
"type": "string",
"kind": "language-code",
"description": "Optional language hint",
"required": false,
"mode": "ValueOrExpression",
"cardinality": "ZeroOrOne",
"role": "Option",
"projection": "Value"
}
},
"output": {
"mode": "Value",
"kind": "text",
"description": "Resolves to the transcribed text"
}
}
}
← openai.tokenize |
all openai.* slots |