rafaelgalle/whisper-test3

Public

3 runs

Run rafaelgalle/whisper-test3 with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
file_path	string		Audio file path
file_url	string		Direct URL to audio
file_string	string		Base64 encoded audio
num_speakers	integer	Min: 1 Max: 50	Number of speakers (leave empty to auto-detect)
translate	boolean	False	Translate to English
language	string		Language code (e.g., 'en', 'pt')
prompt	string		Custom prompt with names/acronyms separated by punctuation
preprocess	integer	0 Max: 4	Preprocessing level: 0=None, 1=Sanitize, 2=+Filter, 3=+ReduceNoise, 4=+Normalize
highpass_freq	integer	45	Highpass filter frequency (Hz)
lowpass_freq	integer	8000	Lowpass filter frequency (Hz)
prop_decrease	number	0.3 Max: 1	Noise reduction proportion
stationary	boolean	True	Use stationary noise reduction
target_dBFS	number	-18	Target loudness in dBFS

{
  "type": "object",
  "title": "Input",
  "required": [
    "num_speakers"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "x-order": 6,
      "nullable": true,
      "description": "Custom prompt with names/acronyms separated by punctuation"
    },
    "file_url": {
      "type": "string",
      "title": "File Url",
      "x-order": 1,
      "nullable": true,
      "description": "Direct URL to audio"
    },
    "language": {
      "type": "string",
      "title": "Language",
      "x-order": 5,
      "nullable": true,
      "description": "Language code (e.g., 'en', 'pt')"
    },
    "file_path": {
      "type": "string",
      "title": "File Path",
      "format": "uri",
      "x-order": 0,
      "nullable": true,
      "description": "Audio file path"
    },
    "translate": {
      "type": "boolean",
      "title": "Translate",
      "default": false,
      "x-order": 4,
      "description": "Translate to English"
    },
    "preprocess": {
      "type": "integer",
      "title": "Preprocess",
      "default": 0,
      "maximum": 4,
      "minimum": 0,
      "x-order": 7,
      "description": "Preprocessing level: 0=None, 1=Sanitize, 2=+Filter, 3=+ReduceNoise, 4=+Normalize"
    },
    "stationary": {
      "type": "boolean",
      "title": "Stationary",
      "default": true,
      "x-order": 11,
      "description": "Use stationary noise reduction"
    },
    "file_string": {
      "type": "string",
      "title": "File String",
      "x-order": 2,
      "nullable": true,
      "description": "Base64 encoded audio"
    },
    "target_dBFS": {
      "type": "number",
      "title": "Target DBFS",
      "default": -18,
      "x-order": 12,
      "description": "Target loudness in dBFS"
    },
    "lowpass_freq": {
      "type": "integer",
      "title": "Lowpass Freq",
      "default": 8000,
      "x-order": 9,
      "description": "Lowpass filter frequency (Hz)"
    },
    "num_speakers": {
      "type": "integer",
      "title": "Num Speakers",
      "maximum": 50,
      "minimum": 1,
      "x-order": 3,
      "description": "Number of speakers (leave empty to auto-detect)"
    },
    "highpass_freq": {
      "type": "integer",
      "title": "Highpass Freq",
      "default": 45,
      "x-order": 8,
      "description": "Highpass filter frequency (Hz)"
    },
    "prop_decrease": {
      "type": "number",
      "title": "Prop Decrease",
      "default": 0.3,
      "maximum": 1,
      "minimum": 0,
      "x-order": 10,
      "description": "Noise reduction proportion"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "segments"
  ],
  "properties": {
    "metrics": {
      "type": "object",
      "title": "Metrics"
    },
    "language": {
      "type": "string",
      "title": "Language"
    },
    "segments": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "title": "Segments"
    },
    "num_speakers": {
      "type": "integer",
      "title": "Num Speakers"
    }
  }
}