AI on demand: Voxtral: Difference between revisions

From MediaWiki
Jump to navigation Jump to search
(Created page with "== Calling the model == <syntaxhighlight lang="bash"> # Set your personal key STONEY_KEY=sk-... # Set the desired model MODEL_ID=mistralai/Voxtral-Mini-3B-2507 # Path to the audio file to transcribe AUDIO_FILE=your-audio-file.wav curl -s https://llm.stoney-cloud.com/v1/audio/transcriptions \ -H "Authorization: Bearer $STONEY_KEY" \ -F "file=@$AUDIO_FILE" \ -F "model=$MODEL_ID" \ | jq . </syntaxhighlight> Example output: <syntaxhighlight lang="json"> { "text...")
 
No edit summary
 
Line 1: Line 1:
== Calling the model ==
== Calling the model ==
<syntaxhighlight lang="bash">
<syntaxhighlight lang="bash">
# Set your personal key
# Set your personal key:
STONEY_KEY=sk-...
STONEY_KEY=sk-...


# Set the desired model
# Set the desired model:
MODEL_ID=mistralai/Voxtral-Mini-3B-2507
MODEL_ID=mistralai/Voxtral-Mini-3B-2507


# Path to the audio file to transcribe
# Path to the audio file to transcribe:
AUDIO_FILE=your-audio-file.wav
AUDIO_FILE=your-audio-file.wav



Latest revision as of 16:59, 2 April 2026

Calling the model

# Set your personal key:
STONEY_KEY=sk-...

# Set the desired model:
MODEL_ID=mistralai/Voxtral-Mini-3B-2507

# Path to the audio file to transcribe:
AUDIO_FILE=your-audio-file.wav

curl -s https://llm.stoney-cloud.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $STONEY_KEY" \
  -F "file=@$AUDIO_FILE" \
  -F "model=$MODEL_ID" \
  | jq .

Example output:

{
  "text": "Hello and welcome to the Stepping Stone LLM Gateway.",
  "usage": {
    "type": "duration",
    "seconds": 4
  }
}

Limitations

The maximum request body size is currently 50 MiB, which limits the size of the audio file.

The following audio formats/containers/codecs are supported: aiff, au, avr, caf, flac, htk, ircam, mat4, mat5, mp3, mpc2k, nist, ogg, paf, pvf, raw, rf64, sd2, sds, svx, voc, w64, wav, wavex, wve, xi