Skip to Content
ModelsGPT Transcription

GPT transcription family

OpenAI’s speech transcription models. Upload audio through POST /v1/audio/transcriptions and get text back.

Model IDs (copy them exactly)
GPT Transcribeopenai/gpt-transcribeBilled per second of audio
GPT-4o mini Transcribeopenai/gpt-4o-mini-transcribeBilled per token

For the common endpoint parameters, see Audio Transcriptions API. For live prices, see the model page . If you need word-level timestamps or speaker diarization, use ElevenLabs Scribe v2.

Examples

gpt_transcribe.py
import os
from openai import OpenAI
 
client = OpenAI(base_url="https://api.ofox.io/v1", api_key=os.environ["OFOX_API_KEY"])
 
with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(
        model="openai/gpt-transcribe",
        file=f,
        language="zh",
        prompt="以下是普通话的句子，请使用简体中文。",
    )
print(result.text)
print(result.usage)

Parameters and billing

Key pointWhen transcribing Mandarin, pass both language and a prompt that asks for Simplified Chinese; otherwise the output may contain Traditional characters.
ItemDescription
language and promptIn our tests, with only language: "zh", gpt-transcribe still output Traditional characters in 1 of 4 runs; after also passing prompt: "以下是普通话的句子，请使用简体中文。", all 4 runs were in Simplified Chinese
response_formatOnly json (default) is supported. verbose_json, text, srt, and vtt all return 400
Response contenttext and usage; no word-level timestamps
Billinggpt-transcribe is billed per second of audio, with usage as {"type": "duration", "seconds": ...}; gpt-4o-mini-transcribe is billed per token, with input_tokens and output_tokens in usage

In our tests, about 9 seconds of Chinese conversation was transcribed in about 2 to 3 seconds.

Common errors

HTTPError messageCauseFix
400response_format 'verbose_json' is not compatible with model 'gpt-transcribe'.GPT transcription models do not support verbose_jsonUse json
400Unsupported response_format 'srt'. Only 'json' and 'verbose_json' are supported on this gatewaytext, srt, or vtt was usedUse json
400Unsupported file format txtThe uploaded file is not audioUpload audio such as mp3 or wav

For more errors, see Audio Transcriptions API.

Official docs

FAQ

GPT transcription outputs Traditional characters for Chinese?

Pass both language: "zh" and prompt: "以下是普通话的句子，请使用简体中文。". In our tests, passing only language still occasionally produced Traditional characters; adding the prompt consistently produced Simplified Chinese.

Can GPT transcription output srt subtitles?

No, only json is supported. If you need timestamps to generate subtitles, use ElevenLabs Scribe v2, which returns start and end times for each word.

How are gpt-transcribe and gpt-4o-mini-transcribe billed?

gpt-transcribe is billed per second of audio; gpt-4o-mini-transcribe is billed per token, with usage shown in the usage field of the response. See the model page for rates.

Last updated on
Gemini TTSDeepSeek