Sign in

v1

latestOpenAPI 3.1.02026-07-2241314.7 KB
Speech-to-Text

Speech to Text (REST)

Convert speech audio to text using Vachana's state-of-the-art Speech-To-Text models.

Features

  • Supports 10 Indian languages with dedicated monolingual models
  • Multilingual support for English and Hindi together
  • Automatic audio format conversion

Supported Languages

LanguageCode
Bengalibn-IN
English (India)en-IN
Gujaratigu-IN
Hindihi-IN
Kannadakn-IN
Malayalamml-IN
Marathimr-IN
Punjabipa-IN
Tamilta-IN
Telugute-IN

Model Selection

  • Single language: Uses the dedicated monolingual model for that language
  • Multiple languages: Uses multilingual model (supports en-IN, hi-IN)

Audio Constraints

  • Maximum duration: 30 seconds (Ideal duration is 30 seconds)
  • Supported formats: WAV, MP3, OGG, FLAC, AAC, M4A
  • Sample rate: Automatically converted to 16000 Hz mono

Response

Returns a JSON object containing:

  • success: Operation status (boolean)
  • timestamp: Request timestamp (format: YYYYMMDD_HHMMSS.mmm)
  • transcript: The transcribed text
post/stt/v3

Response

Successful transcription

successboolean

Indicates if the transcription was successful

timestampstring

Request timestamp in format YYYYMMDD_HHMMSS.mmm

transcriptstring

The transcribed text from the audio

All 4 operations