Whisper_Audio_Processing
Transcribe and analyze audio files sentence by sentence using AI models. Submit audio URLs, customize transcription settings, and retrieve detailed analysis for accurate insights.
Instructions
API for sentece wise transcription and analysis of audio, using AI models. Make sure to call get audio analysis URL with the request ID received from this API.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| audio | Yes | https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav | |
| compression_ratio_threshold | Yes | ||
| condition_on_previous_text | Yes | ||
| logprob_threshold | Yes | ||
| model | Yes | large-v3 | |
| no_speech_threshold | Yes | ||
| suppress_tokens | Yes | ||
| temperature | Yes | ||
| temperature_increment_on_fallback | Yes | ||
| transcription | Yes | plain text | |
| translate | Yes |
Input Schema (JSON Schema)
{
"properties": {
"audio": {
"default": "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
"type": "string"
},
"compression_ratio_threshold": {
"default": 2.4,
"type": "integer"
},
"condition_on_previous_text": {
"default": true,
"type": "boolean"
},
"logprob_threshold": {
"default": -1,
"type": "integer"
},
"model": {
"default": "large-v3",
"type": "string"
},
"no_speech_threshold": {
"default": 0.6,
"type": "integer"
},
"suppress_tokens": {
"default": -1,
"type": "string"
},
"temperature": {
"default": 0,
"type": "integer"
},
"temperature_increment_on_fallback": {
"default": 0.2,
"type": "integer"
},
"transcription": {
"default": "plain text",
"type": "string"
},
"translate": {
"default": false,
"type": "boolean"
}
},
"required": [
"audio",
"model",
"translate",
"temperature",
"transcription",
"suppress_tokens",
"logprob_threshold",
"no_speech_threshold",
"condition_on_previous_text",
"compression_ratio_threshold",
"temperature_increment_on_fallback"
],
"type": "object"
}