DashboardAPI Docs
ChangelogSystem StatusMy Account
DashboardAPI Docs
ChangelogSystem StatusMy Account
  1. Speech to Text API
  • Introduction
  • Voice Library
  • API Authentication
  • Text to Speech API
    • WebSocket
    • Generate TTS
      POST
    • List Voices
      POST
  • VoxFX Effects API
    • Generate TTS with VoxFX
      POST
    • List VoxFX Effects
      GET
  • Voice Cloning API
    • Create Voice Clone
      POST
    • List Voice Clones
      GET
    • Get Single Voice
      GET
    • Edit Voice Clone
      PUT
    • Delete Voice Clone
      DELETE
  • Speech to Speech API
    • Convert Speech to Speech
      POST
  • Speech to Text API
    • Speech to Text API
      POST
    • List Transcription Files
      GET
    • Get Single Transcription
      GET
DashboardAPI Docs
ChangelogSystem StatusMy Account
DashboardAPI Docs
ChangelogSystem StatusMy Account
  1. Speech to Text API

Speech to Text API

POST
https://developer.voicemaker.in/api/v1/speech-to-text
Convert speech to text by uploading an audio file to our transcription API.
Flagship V1, the most accurate transcription model ever, supporting 90+ languages, SRT subtitle generation, and delivers high accuracy on long, complex recordings across diverse speakers, accents, and delivery styles.
Pricing: 5 credits per second of audio

Workflow:#

Audio files 3 minutes or shorter are processed synchronously.
Audio files longer than 3 minutes are automatically processed asynchronously.
For asynchronous jobs, transcription runs in the background and may take additional time depending on file length.
If your audio is processed asynchronously, you can retrieve the transcription status and results using the Get Single Transcription API, which allows you to check pending or completed jobs.
Supported Languages (90+ languages)

Request

Body Params multipart/form-dataRequired

Responses

🟢200
application/json
Transcription accepted or completed
Body

🟠400
🟠401
🟠415
🔴500
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST 'https://developer.voicemaker.in/api/v1/speech-to-text' \
--form 'file=@""' \
--form 'model=""' \
--form 'language="auto"' \
--form 'responseFormat=""' \
--form 'includeSubtitle="false"' \
--form 'tagAudioEvents="false"'
Response Response Example
200 - Success
{
    "success": true,
    "data": {
        "taskId": "6963d6514017c12417a5d2fb",
        "name": "176798484225230676tx65i0xs-voicemaker.in-speech.mp3",
        "fileName": "transcribe-1768150609567472.mp3",
        "speechFile": "https://developer.voicemaker.in/uploads-transcribe/transcribe-1768150609567472.mp3",
        "model": "stt-flagship-v1",
        "generatedText": "Erbongweni prison transfer. Plot to kill Kat Muthala in prison unearthed. Very corrupt senior government officials want Muthala dead before he exposes them.",
        "status": "completed",
        "charge": 225
    },
    "isProcessing": false,
    "usedChars": 225,
    "remainChars": 2417996,
    "remainKeyChars": 2417996
}
Modified at 2026-01-12 18:32:41
Previous
Convert Speech to Speech
Next
List Transcription Files
Built with