Home / Servers / OpenAI API / create_transcription
Create transcription
An MCP tool from the OpenAI API server, hosted on mcp.hjlabs.in.
Create transcription Transcribes audio into the input language. Returns a transcription object in json, diarized_json, or verbose_json format, plain text in text, srt, or vtt format, or a stream of transcript events.… [POST /audio/transcriptions]
Name on the gateway: openai_api__create_transcription · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
file required | string | The audio file object (not file name) to transcribe, in one of these formats… |
model required | string | ID of the model to use. The options are gpt-transcribe, gpt-4o-transcribe… |
language | string | The language of the input audio. Supplying the input language in ISO-639-1… |
languages | array | Possible languages of the input audio, in ISO-639-1 format. Supported by… |
keywords | array | Words or phrases to guide transcription of the input audio. Supported by… |
prompt | string | An optional text to guide the model's style or continue a previous audio… |
response_format | json | text | srt | verbose_json | vtt | diarized_json | The format of the output, in one of these options: json, text, srt… |
temperature | number | The sampling temperature, between 0 and 1. Higher values like 0.8 will make… |
include | array | Additional information to include in the transcription response. logprobs will… |
timestamp_granularities | array | The timestamp granularities to populate for this transcription.… |
stream | boolean | If set to true, the model response data will be streamed to the client as it… |
chunking_strategy | object | Controls how the audio is cut into chunks. When set to "auto", the server… |
known_speaker_names | array | Optional list of speaker names that correspond to the audio samples provided… |
known_speaker_references | array | Optional list of audio samples (as data URLs) that contain known speaker… |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "openai_api__create_transcription",
"arguments": {
"file": "…",
"model": "…"
}
}Or connect the OpenAI API server directly, which lists 371 tools including this one:
claude mcp add --transport http hj-openai-api https://mcp.hjlabs.in/mcp/openai-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the create transcription tool with file set to ….