Generating subtitles from audio

Generate subtitles from audio input

Use case example

  • - Podcast recordings
  • - Transcribing conversations from video files

Added by: APIForAI

Price per call≈ 0.04

License Paper Github

Try it nowAPI information

Try it

Examples

Input

{
"input":{
"audio_path":"https://rbqktisnztholqojxlaf.s..."
"model_name":"base"
"format":"vtt"
}
"id":90
}

Output

{
"status":"succeeded"
"output":{
"language":"english"
"subtitles":"WEBVTT 00:00.000 --> 00:05.000..."
"text":" Hello Marie, I wish you a ver..."
}
"prediction_time":14.188999
}

API Information

Input description

audio_path* uri

Audio file to transcribe

model_name string

An enumeration.

Default value: base

Enum values: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large

format string

An enumeration.

Default value: vtt

Enum values: srt, vtt

Output JSON Schema

This represents the JSON schema that details the structure of the model's output.

{
"type":"object"
"title":"Output"
"required":[
0:"text"
1:"language"
2:"subtitles"
]
"properties":{
"text":{
"type":"string"
"title":"Text"
}
"language":{
"type":"string"
"title":"Language"
}
"subtitles":{
"type":"string"
"title":"Subtitles"
}
}
}

APIForAI

Build fast by accessing AI models easily