embeddings and audio

embeddings and audio API are suitable for semantic search, text-to-speech, audio transcription and audio translation. They continue to use a uniform authentication method:

Authorization: Bearer <MOONNEXAI_API_KEY>

Text embeddings

POST /v1/embeddings

curl https://moonnexai.com/v1/embeddings \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonnexai-embedding",
    "input": "MoonNexAI developer documentation"
  }'

Text transcribing

POST /v1/audio/speech

curl https://moonnexai.com/v1/audio/speech \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Welcome to MoonNexAI.",
    "voice": "alloy",
    "response_format": "mp3"
  }'

Audio transcription

POST /v1/audio/transcriptions

curl https://moonnexai.com/v1/audio/transcriptions \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -F "file=@./speech.mp3" \
  -F "model=whisper-1"

Audio translation

POST /v1/audio/translations

curl https://moonnexai.com/v1/audio/translations \
  -H "Authorization: Bearer <MOONNEXAI_API_KEY>" \
  -F "file=@./speech.mp3" \
  -F "model=whisper-1"

Common field

field	Application API	Annotations
model	All	Model name.
input	embeddings, text transject	Enter the text.
file	transcription, translation	Audio file.
voice	Text to speech	Voice name.
response_format	Text transcribing	Output format, e.g. mp3.

Relevant Pages

• Text Model Matrix
• OpenAI-compatible
• API Reference