FonadaLabs
Login / Sign Up

Kapture V3Latest

You can use our Speech to Text (ASR) API to detect speech and convert it into text. Kapture V3 supports 10 languages from all over India. Same API as Kapture V1, with a smaller language set. This allows for great transcription services, voice commands, subtitles, and voice-enabled applications, promising high accuracy with support for various accents, dialects, and audio formats.

Quick start

  1. 1

    Get an API key

    Create a key in the Console and replace YOUR_API_KEY in the examples below.

  2. 2

    Install the SDK

    pip install fonadalabs
  3. 3

    Make your first request

    Transcribe an audio file. Replace audio.wav with your file and set the language code.

    from fonadalabs import ASRClient

client = ASRClient(api_key="YOUR_API_KEY")

result = client.transcribe_file("audio.wav", language_id="hi", model="v3")
print(result.text)

Overview

Our ASR (Automatic Speech Recognition) API converts spoken language into written text with high accuracy and low latency. Our models are trained on diverse datasets covering multiple languages, accents, and speaking styles across India to ensure reliable transcription service across various use cases.

  • Long-audio file transcription in a single request (any length, up to 25MB)
  • Batch processing for audio file transcription

Try a sample transcription:

Sample Audio
Hindi Female Voice
00:08Clear Audio
Transcription:
"नमस्ते, मेरा नाम श्रुति है। बताइए, मैं आपकी किस तरह मदद कर सकती हूँ।"

Explore our voice library to find the perfect voice for your project.

Developer quickstart

Learn how to integrate text to speech into your applications

API Usage

Use our models to convert speech to text using REST API endpoint with simple requests for single and batch transcribing.

Transcribe Audio File - Basic Request

You can transcribe a single audio using the endpoint which returns the transcript immediately after processing.

curl
curl -X POST https://api.fonada.ai/v3/asr/transcribe \ -H "Authorization: Bearer YOUR_API_KEY" \ -F "file=@audio.wav" \ -F "language_id=hi"

Request Parameters

ParameterTypeRequiredDescription
filefile✓Audio: wav, mp3, flac, m4a, ogg, opus, aac. Any length. Max 25MB.
language_idstring✓Language code (e.g. , "hi" for Hindi, "en" for English).

Response Format

{
  "job_id": "3d02014b-6ddf-45e3-94bc-8e6f69da6834",
  "text": "Sir नहीं ऐसा कुछ होता तो मैं बताता है ऐसा कुछ नहीं है sir.",
  "language": "hi",
  "audio_duration_s": 3.12,
  "num_chunks": 1,
  "chunk_durations_s": [3.12],
  "chunk_texts": ["Sir नहीं ऐसा कुछ होता तो मैं बताता है ऐसा कुछ नहीं है sir."],
  "transcript_chunks": [
    {
      "idx": 0,
      "text": "Sir नहीं ऐसा कुछ होता तो मैं बताता है ऐसा कुछ नहीं है sir.",
      "duration_s": 3.12,
      "start_s": 0.0,
      "end_s": 3.12
    }
  ],
  "bucket": null,
  "storage_prefix": null,
  "processing_time_ms": 1731.9,
  "credits_used": 9
}

Fonadalabs SDK

You can get richer ASR experiences with our official SDK. Install it once and tap into high-level modules for file, batch, and custom transcription workflows.

Install the SDK

pip
pip install fonadalabs

Transcribe a Single File

You can use high-level HTTP client to submit local recordings. The SDK falls back to values from .env, so you can keep credentials out of source control while overriding settings at runtime.

Python
from fonadalabs import ASRClient AUDIO_PATH = "your_audio_path" LANG = "hi" your_api = "your_api_key" if __name__ == "__main__": client = ASRClient(api_key=your_api) try: result = client.transcribe_file( AUDIO_PATH, language_id=LANG, model="v3", ) print("Transcription Complete") print("----------------------------") print(f"Language : {result.language_id}") print(f"Text : {result.text}") print(f"Duration : {result.audio_duration_s}s") print(f"Chunks : {result.num_chunks}") print(f"Credits : {result.credits_used}") print("----------------------------") except Exception as e: print(f"Error: {e}") finally: client.close()

Supported Formats

Audio: wav, mp3, flac, m4a, ogg, opus, aac. Any length. Max 25MB.

MP3

Sample rates: 8kHz - 48kHz

Channels: Mono/Stereo

Bit rate: 16bit/24bit

WAV

Sample rates: 8kHz - 48kHz

Channels: Mono/Stereo

Bit rate: 16bit/24bit

FLAC

Sample rates: 8kHz - 48kHz

Channels: Mono/Stereo

Bit rate: 16bit/24bit

M4A

Sample rates: 8kHz - 48kHz

Channels: Mono/Stereo

Bit rate: 16bit/24bit

OGG

Sample rates: 8kHz - 48kHz

Channels: Mono / Stereo

Bit rate: 16bit/24bit

OPUS

Any length. Max 25MB.

AAC

Any length. Max 25MB.

Supported Languages

Kapture V3 supports 10 languages with optimized accuracy for regional accents and dialects. This is the only difference from Kapture V1. Any other language_id returns 400 unsupported_language before credits are charged.

LanguageCodeNative Name
EnglishenEnglish
Bengalibnবাংলা
Gujaratiguગુજરાતી
Hindihiहिन्दी
Kannadaknಕನ್ನಡ
Malayalammlമലയാളം
Marathimrमराठी
Punjabipaਪੰਜਾਬੀ
Tamiltaதமிழ்
Teluguteతెలుగు

Pricing

Priced per hour, billed per second of audio.

ModelPriceCreditsBilling
Kapture V1 / V3₹24.19 per hour2,016 creditsBilled per second

The same rate applies to single-file and long-audio requests. See the full pricing page.

Streaming is available on Kapture V1 only.

Best Practices

Follow these recommendations to achieve optimal transcription accuracy and performance.

Audio Quality

  • • Use high-quality microphones and recording equipment
  • • Record in quiet environments with minimal background noise
  • • Maintain consistent distance from the microphone
  • • Use 16kHz+ sample rate for better accuracy

Speaking Guidelines

  • • Speak clearly and at a moderate pace
  • • Avoid speaking too fast or too slow
  • • Use natural pauses between sentences
  • • Minimize overlapping speech in multi-speaker scenarios

Error Handling

  • • Implement retry logic for network failures
  • • Check language_id against the supported list to avoid 400 unsupported_language
  • • Monitor API rate limits and usage quotas
Back to Kapture V1