Speech to text
Whisper Medium Nepali
A Nepali-specialized Whisper Medium route for direct transcription.
- Status
- Live
- Languages
- Nepali
- License
- Not declared (Whisper base: MIT)
Model ID
| Model ID | Designed for |
|---|---|
whisper-nepali-medium | Nepali-specialized speech transcription |
Confirm access with GET /v1/models, then follow the utility-model docs for the canonical v1 REST or native gRPC request contract.
Pricing
whisper-nepali-medium: Free for a limited time. $0.00006 $0.00 per audio second
Overview
Whisper Medium Nepali is a CTranslate2 build specialized for Nepali speech. Use
the whisper-nepali-medium alias with
POST /v1/audio/transcriptions or the native gRPC transcription
method.
When to pick it
- The source language is Nepali and transcription quality matters more than broad language detection.
- You want a smaller Nepali-focused route than Whisper Large v3.
- The application needs Nepali text, not an English translation.
When to pick something else
- Unknown or mixed source languages → Whisper Large v3
- Translation into English → Whisper Large v3
- A compact broadly multilingual Apache 2.0 route → Qwen3-ASR
Pass language=ne for an explicit source-language hint. This alias
supports transcription only; it is not accepted by
POST /v1/audio/translations. Use model discovery and your
organization limits as the source of truth for access and request limits.