Skip to main content

LiveKit Agents plugin for Gnani Vachana speech AI — STT & TTS for Indian languages

Project description

livekit-plugins-gnani

PyPI License

LiveKit Agents plugin for Gnani Vachana — high-accuracy Speech-to-Text and low-latency Text-to-Speech for Indian languages.

Vachana is a production-ready speech AI platform by Gnani.ai supporting 10+ Indian languages with real-time streaming, multilingual transcription, and code-switching capabilities.

Installation

pip install livekit-plugins-gnani

This will also install the gnani-vachana core SDK as a dependency.

Prerequisites

You need a Gnani API key. Email speechstack@gnani.ai to get started — all new accounts receive free credits, no credit card required.

Set your credentials as environment variables:

export GNANI_API_KEY="your-api-key"

# For REST STT only (optional):
export GNANI_ORGANIZATION_ID="your-org-id"
export GNANI_USER_ID="your-user-id"

Quick Start

Speech-to-Text

from livekit.plugins.gnani import STT

stt = STT(language="hi-IN")

# Use with a LiveKit voice agent pipeline

Text-to-Speech

from livekit.plugins.gnani import TTS

tts = TTS(voice="sia")

# Use with a LiveKit voice agent pipeline

Features

STT

  • Batch recognition — REST API (POST /stt/v3) for file-based transcription
  • Real-time streaming — WebSocket API for live audio transcription with VAD
  • 10 Indian languages — bn-IN, en-IN, gu-IN, hi-IN, kn-IN, ml-IN, mr-IN, pa-IN, ta-IN, te-IN
  • Code-switching — Hinglish (en-hi-IN-latn) and Hindi-English mixed (en-hi-in-cm) for streaming
  • Sample rates — 8 kHz and 16 kHz

TTS

  • Chunked synthesis — REST API for single-request audio generation
  • Real-time streaming — WebSocket API for low-latency streaming synthesis
  • 8 voices — sia, raju, kanika, nikita, ravan, simran, karan, neha
  • Configurable output — sample rate (8000–44100), encoding (linear_pcm, oggopus), container (raw, mp3, wav, mulaw, ogg)

Supported Languages

Language Code
Bengali bn-IN
English (India) en-IN
Gujarati gu-IN
Hindi hi-IN
Kannada kn-IN
Malayalam ml-IN
Marathi mr-IN
Punjabi pa-IN
Tamil ta-IN
Telugu te-IN

Available Voices

Voice ID
Sia sia
Raju raju
Kanika kanika
Nikita nikita
Ravan ravan
Simran simran
Karan karan
Neha neha

Architecture

gnani-vachana           ← Core SDK (REST, WebSocket, SSE clients)
    ↑
livekit-plugins-gnani   ← This package (LiveKit Agents adapter)

This plugin is a thin adapter that wraps the gnani-vachana SDK into LiveKit's stt.STT and tts.TTS base classes. All connection logic, authentication, and audio format handling lives in the core SDK.

Documentation

License

Apache 2.0 — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

livekit_plugins_gnani-0.2.0.tar.gz (9.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

livekit_plugins_gnani-0.2.0-py3-none-any.whl (12.1 kB view details)

Uploaded Python 3

File details

Details for the file livekit_plugins_gnani-0.2.0.tar.gz.

File metadata

  • Download URL: livekit_plugins_gnani-0.2.0.tar.gz
  • Upload date:
  • Size: 9.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for livekit_plugins_gnani-0.2.0.tar.gz
Algorithm Hash digest
SHA256 aff16ed4c60d00906e01e76f6114c0f94fb67a7d2ac720176e7af2afd99f0563
MD5 52889703914907c01124651aa8a2b044
BLAKE2b-256 2bcb0833a5ea925709d4d8cbf845a53f8784b005489163437e681949cb8ac7be

See more details on using hashes here.

Provenance

The following attestation bundles were made for livekit_plugins_gnani-0.2.0.tar.gz:

Publisher: workflow.yml on Gnani-AI-Mintlify/livekit-plugins-gnani

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file livekit_plugins_gnani-0.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for livekit_plugins_gnani-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 57bd9b1002d742ce4fcc1b51e45b19cd97c129b2301fbf40dc89b5869a62f6d3
MD5 b22a6320f1bdebbf7a45c0c02144e5ce
BLAKE2b-256 527d1aa6ff6612bacb7bcdd0d08571757e36c75abca148f75d67fcb4694660e1

See more details on using hashes here.

Provenance

The following attestation bundles were made for livekit_plugins_gnani-0.2.0-py3-none-any.whl:

Publisher: workflow.yml on Gnani-AI-Mintlify/livekit-plugins-gnani

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page