Skip to main content
In this quickstart, you’ll send an audio file to the STT API and receive a transcript.

​
Make your first STT API request

1

Create an API key

Create an Inworld account.In Inworld Portal, generate an API key by going to Settings > API Keys. Copy the Base64 credentials.Set your API key as an environment variable.
export INWORLD_API_KEY='your-base64-api-key-here'
2

Prepare an audio file

The STT API accepts base64-encoded audio. Prepare your audio file (e.g., input.mp3) and encode it:
export AUDIO_BASE64=$(base64 input.mp3 | tr -d '\n')
Recommended audio settings: 16,000 Hz sample rate, mono, 16-bit depth. See Supported Audio Formats for all options.
3

Send the request

cURL
 curl --request POST \
   --url https://api.inworld.ai/stt/v1/transcribe \
   --header "Authorization: Basic $INWORLD_API_KEY" \
   --header "Content-Type: application/json" \
   --data "{
     \"transcribeConfig\": {
       \"modelId\": \"groq/whisper-large-v3\",
       \"audioEncoding\": \"MP3\"
     },
     \"audioData\": {
       \"content\": \"$AUDIO_BASE64\"
     }
   }"
Set audioEncoding to match your file format (MP3, LINEAR16, OGG_OPUS, FLAC), or use AUTO_DETECT to let the API infer it from the audio header.
4

Review the response

A successful response contains the transcript:
{
  "transcription": {
    "transcript": "Hey, I just wanted to check in on the delivery status for my order.",
    "isFinal": true,
    "wordTimestamps": []
  },
  "usage": null
}
FieldDescription
transcription.transcriptThe transcribed text
transcription.isFinalWhether the result is finalized
transcription.wordTimestampsPer-word timing data (coming soon)
usageUsage metrics for billing (coming soon)

​
Next Steps

STT Overview

Learn about supported providers, audio formats, and endpoints.

API Reference

View the complete API specification.