Audio transcription and translation

Audio transcription is used to convert audio into text; audio translation is used to translate audio content into the target language. Both types of API are used to upload audio files on multipart forms.

API Path

Methodology	Path	Purpose
POST	/v1/audio/transcriptions	Audio transcription.
POST	/v1/audio/translations	Audio translation.

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	Annotations
file	Audio file.
model	transcription or translation model name.
language	Enter a language hint, which is based on API Reference.
response_format	Returns formats such as json or text.

response Processing

scene	Treatment
Normal Text	Saves transcription text, filename and model name.
Subtitles scene	Saves the text of the subparagraphs and the time information, which is the return format.
Long Audio	Slice-processing merges text by business ID.

Access Recommendations

• Confirm that the audio is clear before upload and minimize background noise.
• Long audio suggests first slice and then merge the results by business ID.
• Saves the text of the segment, time information and original file name when subtitles are required.

Relevant Pages

• Vector & Audio Summary
• Text Model Matrix
• Text-to-Speech
• API Reference