Plan a speech-to-text API for audio transcription.

01 / WORKFLOW

Verify transcription access before selecting a model

The public catalogue does not reliably identify transcription capability for every audio entry. Do not infer support from a model name, vendor or billing unit. The example deliberately retains YOUR_TRANSCRIPTION_MODEL until a supported model is confirmed. Use the audio reference and your available account options to establish the model ID, accepted file types and request limits.

02 / WORKFLOW

Upload a file using multipart form data

Send the audio file as the file field alongside the model identifier and accepted transcription settings. Let your HTTP client produce the multipart boundary; do not label the whole request as application/json. Check size and format before upload. Optional language, prompt or response-format fields should follow the selected model and endpoint instead of being assumed to work everywhere.

03 / WORKFLOW

Read the chosen format and design for uncertain results

Parse the response according to the requested supported format. Plain text and structured transcription results need different handling. Preserve enough application context to associate a result with its original recording. Low-quality recordings, background noise and specialized vocabulary can reduce transcription quality, so review representative audio and offer a correction step when accuracy matters. Diagnose upload failures separately from model errors.

Request example

This example does not execute automatically. Verify the current model and parameters, then set these environment variables on your server. Replace any YOUR_* placeholders with confirmed supported values.

export ALLGATE_BASE_URL='https://api.allgate.ai/v1'
export ALLGATE_API_KEY='YOUR_API_KEY'

# speech-to-text: multipart/form-data upload
curl --fail-with-body --silent --show-error "$ALLGATE_BASE_URL/audio/transcriptions" \
  -H "Authorization: Bearer $ALLGATE_API_KEY" \
  -F model='YOUR_TRANSCRIPTION_MODEL' \
  -F response_format=json \
  -F file=@sample.wav

Check models and current availability

These entries come from the public catalogue build snapshot. A listing does not guarantee endpoint capability or continuing supply. For audio, verify synthesis or transcription support separately. Open a model to check its exact ID, settings and billing unit.

Catalogue snapshot: 2026-10-30

This catalogue snapshot has no matching model entries for this workflow. Check the live catalogue before integrating and do not guess a model ID.

Costs and workflow limits

Check the exact transcription model’s published billing unit and your account quote. Do not apply a speech-synthesis character rate to an audio upload. Endpoint documentation describes a request contract, not a promise of currently available transcription supply or a fixed price. Verify both before accepting customer jobs.