Input Schema
{
"body": {
"audio_base64": "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"
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Output Schema
{
"example": {
"limitations": [
"Probabilities are model scores, not calibrated confidences; short sections (under about 2 s), accents and code-switching inside one section lower reliability.",
"Our checks used synthetic English speech; for other languages accuracy follows Whisper base and is lower for languages with little training data.",
"With candidates the answer is always one of them, even when the recording is in another language."
],
"result": {
"alternatives": [
{
"language": "en",
"name": "English",
"probability": 0.969
},
{
"language": "de",
"name": "German",
"probability": 0.003
},
{
"language": "pt",
"name": "Portuguese",
"probability": 0.003
}
],
"audio": {
"bytes": 1197,
"channels": 1,
"codec": "opus",
"duration_s": 1.42,
"sample_rate": 48000,
"sha256": "3af127aff1c1cf5d827731c34d4476c1d820bde2428840e9500b303c5905cd63"
},
"candidates": null,
"language": "en",
"language_name": "English",
"languages_found": [
"en"
],
"model": {
"files": [
"onnx/encoder_model_quantized.onnx",
"onnx/decoder_model_merged_quantized.onnx"
],
"license": "MIT (OpenAI Whisper weights and code); ONNX export Xenova/whisper-base under Apache-2.0 per its model card",
"model": "OpenAI Whisper base (74 M parameters)",
"onnx": "https://huggingface.co/Xenova/whisper-base/tree/64da57285918e20ea79ea5c88eed7197933abaa8",
"runtime": "onnxruntime-node 1.31 (CPU), greedy decoding",
"vad": "Silero VAD v6.2"
},
"probability": 0.969,
"sections": [
{
"alternatives": [
{
"language": "en",
"name": "English",
"probability": 0.969
},
{
"language": "de",
"name": "German",
"probability": 0.003
},
{
"language": "pt",
"name": "Portuguese",
"probability": 0.003
}
],
"duration_s": 1.07,
"end": 1.42,
"language": "en",
"language_name": "English",
"probability": 0.969,
"start": 0.35
}
],
"skipped_sections": [],
"speech_s": 1.07
},
"service": "spoken-language-id",
"status": "success"
},
"type": "json"
}