Key Capabilities
- 10 Indian Languages: Comprehensive support for major Indian languages with native script transcription
- Intelligent Language Detection: Automatic identification or preference-guided transcription for ambiguous audio
- Universal Audio Support: Send any common format - automatic conversion handles WAV, MP3, FLAC, OGG, M4A, WebM
Quick Start Guide
Get your first transcription in under 5 minutes.Prerequisites
Before you begin, ensure you have:- Valid API credentials (API Key and User ID)
- An audio file for testing (WAV, MP3, FLAC, or other common formats)
- cURL installed, or a tool like Postman for making HTTP requests
- Audio file meets constraints: ≤ 60 seconds duration, mono/stereo channel
Your First API Call
Here’s a minimal example to transcribe a Hindi audio file:<x-api-key>: Your Vachana API key<x-api-request-id>: Your Vachana request ID<x-api-user-id>: Your Vachana user ID<x-organization-id>: Your Vachana organization ID/path/to/your/audio.wav: Path to your audio filehi-IN: Language code (see Language Codes for all options)
Expected Response
On success, you’ll receive a JSON response like this:Authentication Setup
The Vachana STT API uses header-based authentication with two required credentials.Obtaining Credentials
API key provisioning is currently handled by our team to ensure personalized onboarding and support. To request your credentials: Send an email to speechstack@gnani.ai with the following details:- Person Name: Your full name
- Company Name: Your organization name
- Use Case (optional): Brief description of your intended application
- Our team will generate your API credentials (
api-keyanduser-id) - You’ll receive a ready-to-use cURL command with your credentials embedded
- We’ll assign free credits to your account so you can start testing immediately—no payment required
- You can begin transcribing right away using the provided cURL example
Next Steps
- Review the API Reference for all available parameters