Model reference · open weights

IndicVoice

Available as managed deployment Audio Bindkushal · community Text→speech 1 variants 1k dl/mo

IndicVoice is an open-weight audio or speech model from Bindkushal. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byBindkushal
TypeAudio & music
TaskText→speech
Released2026-04-08
Popularity1k downloads / month
LicenceOpen weights

About

What IndicVoice is

A decoder-only neural TTS model for Indian languages, built on the Kokoro-82M architecture with a native Indic G2P frontend.

Author: Kushal Kant Bind — Chandigarh University Project: GSoC 2026, Sugar Labs GitHub: Bindkushal/indic-voice


Read the full model card

Quick Start

pip install git+https://github.com/Bindkushal/indic-g2p.git
pip install git+https://github.com/Bindkushal/indic-voice.git
apt-get install espeak-ng
from indicvoice import IndicPipeline
pipeline = IndicPipeline(lang_code="hi", repo_id="Bindkushal/IndicVoice-82M")
for gs, ps, audio in pipeline("नमस्ते दुनिया", voice="af_heart"):
    import soundfile as sf
    sf.write("output.wav", audio, 24000)

Files in This Repo

FileDescription
config.jsonModel architecture config
indicvoice-v1_0.pthModel weights (82M params)
voices/af_heart.ptDefault voice style tensor
voices/af_bella.ptVoice style tensor
voices/am_adam.ptVoice style tensor

Supported Languages

LanguageCodeScriptStatus
HindihiDevanagariReady
PunjabipaGurmukhiReady
BengalibnBengaliBeta
EnglishenRomanReady

Architecture

  • Base: Kokoro-82M (StyleTTS2 + ISTFTNet), Apache 2.0
  • G2P: indic-g2p — native Indic phonemizer
  • Fallback: espeak-ng for OOV words
  • Parameters: 82M
  • Sample rate: 24000 Hz

Citation

@misc{bind2026indicvoice,
  title={IndicVoice: Decoder-Only Neural TTS with Native G2P for Indian Languages},
  author={Kushal Kant Bind},
  year={2026},
  institution={Chandigarh University},
  note={GSoC 2026, Sugar Labs}
}

Acknowledgements

  • hexgrad/kokoro — base TTS architecture (Apache 2.0)
  • AI4Bharat — IndicVoices-R dataset
  • IIT Madras — IndicTTS dataset

License

Apache 2.0

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys indicvoice for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (indicvoice below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="indicvoice" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms