Gpt 4o Transcribe

gpt-4o-transcribe

post

Speech-to-text model powered by GPT-4o

Header parameters

AuthorizationstringRequiredExample: sk-qNXaCLFLuF6KxswYB31dF9Fb5c6c4d929dE30957A6Fa0047

Body

multipart/form-data

modelstringRequired

model is the model name

Example: gpt-4o-transcribe

filestring · binaryRequired

The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

Example: file:///Users/andrewsmac/Downloads/response.mpga

chunking_strategystringOptional

Controls how the audio is cut into chunks. When set to "auto", the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. server_vad object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block.

Default: autoExample: auto

includestring[]Optional

Additional information to include in the transcription response. logprobs will return the log probabilities of the tokens in the response to understand the model's confidence in the transcription. logprobs only works with response_format set to json.

known_speaker_namesstring[]Optional

Optional list of speaker names that correspond to the audio samples provided in known_speaker_references[]. Each entry should be a short identifier (for example customer or agent). Up to 4 speakers are supported.

known_speaker_referencesstring[]Optional

Optional list of audio samples (as data URLs) that contain known speaker references matching known_speaker_names[]. Each sample must be between 2 and 10 seconds, and can use any of the same input audio formats supported by file.

languagestringOptional

The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

Example: en

promptstringOptional

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

response_formatstring · enumOptional

The format of the output, in one of these options: json, text, srt, verbose_json, vtt, or diarized_json.

Default: jsonExample: jsonPossible values:

temperaturenumber · max: 1Optional

The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Default: 0Example: 0.8

Responses

200

The audio file content.

application/json

post

/audio/transcriptions

HTTPcURLJavaScriptPython

POST /v1/audio/transcriptions HTTP/1.1
Host: audio.onerouter.pro
Authorization: text
Content-Type: multipart/form-data
Accept: */*
Content-Length: 253

{
  "model": "gpt-4o-transcribe",
  "file": "file:///Users/andrewsmac/Downloads/response.mpga",
  "chunking_strategy": "auto",
  "include": "",
  "known_speaker_names": "",
  "known_speaker_references": "",
  "language": "en",
  "prompt": "",
  "response_format": "json",
  "temperature": 0.8
}

200

The audio file content.

{
  "text": "A cute baby sea otter!"
}