Skip to main content

​
Overview

NanoGPT provides a drop-in OpenAI-compatible endpoint for speech-to-text (STT) transcription.

​
Endpoint

POST https://nano-gpt.com/api/v1/audio/transcriptions

​
Authentication

Use either header:
  • Authorization: Bearer YOUR_API_KEY
  • x-api-key: YOUR_API_KEY

​
Request Formats

​
1) Multipart upload (OpenAI-compatible)

Send multipart/form-data with:
  • file (required): audio (or video for supported models)
  • model (required): STT model ID
  • language (optional): language code (default: auto-detect)
curl -X POST https://nano-gpt.com/api/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F [email protected] \
  -F model=Whisper-Large-V3 \
  -F language=en

​
2) JSON with URL

{
  "model": "Whisper-Large-V3",
  "file_url": "https://example.com/audio.mp3",
  "language": "en"
}
NanoGPT accepts file_url or audio_url for URL-based transcription.

​
Supported Models (Examples)

Model availability changes; use GET /api/v1/models?detailed=true for discovery.
ModelNotes
Whisper-Large-V3High-accuracy transcription
WizperFast processing
Elevenlabs-STTSpeaker diarization + audio event tagging
gpt-4o-mini-transcribeImproved accuracy vs Whisper (OpenAI-family)
openai-whisper-with-videoAccepts video files (MP4, MOV, etc.)

​
Voice Cloning (via the same endpoint)

Some special model IDs run voice-cloning workflows instead of returning plain transcription text:
  • qwen-voice-clone — returns a reusable speaker embedding URL
  • minimax-voice-clone — returns a reusable custom voice ID (and/or preview output)

​
Response

{
  "text": "The transcribed text goes here.",
  "language": "en",
  "duration": 45.2
}

​
Supported Formats

  • Audio: MP3, OGG, WAV, M4A, AAC
  • Video (model-dependent): MP4, MOV, AVI, MKV, WEBM

​
Example (Python, OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://nano-gpt.com/api/v1",
    api_key="YOUR_API_KEY"
)

with open("audio.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="Whisper-Large-V3",
        file=audio_file
    )

print(transcript.text)

​
See Also

  • NanoGPT transcription workflows: api-reference/endpoint/transcribe.mdx
  • Full STT guide and model list: api-reference/speech-to-text.mdx