Hugging Face's logo

buggandhi
/
Orqanta-Voice

Text-to-Speech
Safetensors
orqanta_voice
tts
audio
speech
indic
streaming
Model card Files
xet
 Community

Orqanta-Voice

Orqanta-Voice

Streaming multilingual text-to-speech for 11 Indic languages and English, with 20 built-in voices and zero-shot voice cloning. This repository is the inference engine: a continuous-batching CUDA-graph engine, a Python API, an OpenAI-compatible HTTP server and a WebSocket streaming server. The weights are on Hugging Face at buggandhi/Orqanta-Voice.

Open In Colab

Samples · Model card · Engine docs · Text normaliser

The Python package and model are called Orqanta-Voice (module name: orqanta_voice).

  • Languages: as bn en gu hi kn ml mr or pa ta te.
  • Streaming: about 14 ms to first audio at B=1 on an H100. One H100 NVL serves 224 concurrent streams at 323 s of audio per second, with steady-state TTFA p99 242 ms and 0 playback stalls.
  • Voices: 20 named voices (voice="Ahana"), or clone a voice from 3-10 s of audio.
  • Text normaliser (bundled): numbers, currency, dates, URLs and ALL-CAPS names are spoken correctly in every language.

Install

You need Python 3.10-3.12, Linux and an NVIDIA GPU with a CUDA 12.8 driver (8 GB or more of GPU memory).

git clone https://github.com/GANDHIKALASI/Orqanta-Voice orqanta_voice && cd orqanta_voice
python -m venv .venv && . .venv/bin/activate
pip install -e ".[server]" --extra-index-url https://download.pytorch.org/whl/cu128

The pinned runtime is torch 2.8.0 (cu128, triton 3.4.0), transformers 5.6.2 and speechbrain 1.1.2. Weights, the Mimi codec and the ECAPA speaker encoder are downloaded from Hugging Face on first use. Set HF_HUB_OFFLINE=1 to use only the local cache.

Quickstart

Python 

from orqanta_voice import OrqantaVoiceTTS
import soundfile as sf

tts = OrqantaVoiceTTS.from_pretrained("buggandhi/Orqanta-Voice", max_seats=16)

wav = tts.generate("नमस्ते, आपका ऑर्डर कल पहुँच जाएगा।", lang="hi", voice="Ahana")
sf.write("out.wav", wav, 24000)                       # float32, 24 kHz mono

for pcm in tts.stream("Your OTP is 482913.", lang="en", voice="Siddhant", normalize=True):
    ...                                                # int16 PCM chunks, as they are generated

generate, stream and astream are thread-safe and asyncio-safe. Concurrent calls are batched on the GPU.

Command line 

python examples/synthesize.py "నమస్కారం, మీరు ఎలా ఉన్నారు?" --lang te --voice Sreekar -o out.wav
python examples/synthesize.py --list-voices

HTTP server (OpenAI-compatible) and WebSocket streaming 

python -m orqanta_voice.server --ckpt buggandhi/Orqanta-Voice --host 0.0.0.0 --port 8080 --max-seats 64

curl -sN localhost:8080/v1/audio/speech -H 'content-type: application/json' \
  -d '{"input":"Your order has shipped.","language":"en","voice":"Ahana","response_format":"wav"}' > out.wav

from openai import OpenAI          # any OpenAI-compatible client
client = OpenAI(base_url="http://localhost:8080/v1", api_key="unused")
with client.audio.speech.with_streaming_response.create(
        model="orqanta-voice", voice="Ahana", input="Hello from Orqanta-Voice.", response_format="pcm") as r:   # s16le, 24 kHz
    for chunk in r.iter_bytes():
        ...
  • POST /v1/audio/speech streams wav, pcm, mp3 or opus; flac is sent once the audio is complete.
  • WS /v1/tts/stream carries several concurrent contexts per socket, with cancel and binary frames. See examples/ws_stream.py and the protocol in the docstring of orqanta_voice/server.py.
  • GET/POST/DELETE /v1/voices manages cloned voices, and GET /health reports status.
  • Text is normalised by default. Turn this off with "normalize": false per request, or --no-normalise for the whole server.
  • orqanta_voice.client has a small Python client for HTTP and WebSocket.

Voices

voice gender age languages (>= 1 h trained) description
Ahana female young bn en gu hi kn ml mr or pa ta te Young female voice, bright, youthful
Vaidehi female adult bn en gu hi kn ml mr or pa ta te Adult female voice, calm, gentle
Malini female mature bn en gu hi kn ml mr or pa ta te Mature female voice, steady narrator
Charvi female young bn en gu hi kn ml mr or pa ta te Young female voice, energetic, upbeat
Jahnavi female adult bn en gu hi kn ml mr or ta te Adult female voice, warm, friendly
Anirban male adult bn en gu hi kn ml mr or pa ta te Adult male voice, steady narrator
Nakul male young bn en gu hi kn ml mr or pa ta te Young male voice, bright, youthful
Vasant male mature bn en gu hi kn ml mr or ta te Mature male voice, steady narrator
Siddhant male adult bn en gu hi kn ml mr or pa ta te Adult male voice, clear, professional
Satvik male young bn en gu hi kn ml mr or pa ta te Young male voice, warm, friendly
Abhay male adult en hi Adult male voice, natural conversational style; trained on English, Hindi
Nivedita female adult en hi Adult female voice, natural conversational style; trained on English, Hindi
Ishwari female adult hi Adult female voice, natural conversational style; trained on Hindi
Ritvik male adult hi Adult male voice, natural conversational style; trained on Hindi
Vrinda female young hi Young female voice, natural conversational style; trained on Hindi
Sreekar male adult en hi te Adult male voice, natural conversational style; trained on English, Hindi, Telugu
Kayal female adult en ta Adult female voice, natural conversational style; trained on English, Tamil
Shaunak male young en hi Young male voice, natural conversational style; trained on English, Hindi
Akshat male adult en hi Adult male voice, natural conversational style; trained on English, Hindi
Tanushree female adult en hi Adult female voice, natural conversational style; trained on English, Hindi
  • Every voice can speak all 12 languages. Languages outside its trained list are spoken cross-lingually.
  • Names are case-insensitive. tts.voices (a property) and GET /v1/voices list them.
  • The voices are synthetic personas and must not be presented as real people.

Named-voice prompt format. A named voice is selected by its name in the prompt: the engine renders <|lang:xx|>{Name}: <text><|audio|>. Send only your text with voice="Name" (Python) or "voice": "Name" (HTTP/WS). Do not type {Name}: yourself, and do not combine a named voice with a reference clip. Each voice's conditioning mode is in voices/voices.json:

  • named uses the trained name prompt;
  • spk uses a stored speaker embedding.

Voice cloning 

# 3-10 s of clean speech + its exact transcript and language. Only clone voices you have consent to use.
tts.register_voice("my_voice", ref_audio="ref.wav", ref_text="<exact transcript of ref.wav>", lang="hi")
wav = tts.generate("வணக்கம், எப்படி இருக்கிறீர்கள்?", lang="ta", voice="my_voice")   # cross-lingual

# one-off (cached for the session):
wav = tts.generate("Hello!", lang="en", ref_audio="ref.wav", ref_text="...", ref_lang="hi")

There are three conditioning modes for a reference:

  • icl_spk (default): the reference audio as an in-context prompt, plus its ECAPA embedding;
  • icl: the reference audio only;
  • spk: the ECAPA embedding only, so no transcript is needed.

The reference language can differ from the target language. Over HTTP, POST /v1/voices registers a clone (see examples/clone_voice.py). Zero-shot clones are recognisably close to the reference but not identical.

Languages

code language CER % (Qwen3-ASR, release bench)
as Assamese 6.59
bn Bengali 2.83
en English 1.74
gu Gujarati 3.76
hi Hindi 2.05
kn Kannada 2.72
ml Malayalam 4.20
mr Marathi 2.09
or Odia 4.33
pa Punjabi 3.32
ta Tamil 4.55
te Telugu 2.64

Overall CER on the 6,000-clip release bench is 3.40 % (Qwen3-ASR). Real failures, where two ASRs agree, are 0.15 %. The model card describes the method in full.

Streaming performance

The whole release bench (6000 texts, 20.3 h of audio) was served by orqanta_voice.server with its defaults, as 224 concurrent WebSocket streams on one H100 NVL:

metric value
throughput 323 audio-s/s
TTFA, steady state, p50 / p90 / p99 111 / 134 / 242 ms
TTFA, whole run incl. ramp and drain, p50 / p99 115 / 774 ms
playback stalls / errors 0 / 0
B=1 (single stream, H100) TTFA about 14 ms, RTF about 0.13

GPU memory, with a bf16 backbone, an fp16 depth decoder and 2048 KV tokens per seat (add about 0.5 GB of CUDA context):

max_seats steady peak
1 7.7 GB 9.2 GB
8 9.7 GB 10.9 GB
16 11.7 GB 12.8 GB
32 15.8 GB 16.5 GB

An RTX 4090 (24 GB) serves 48 streams at capacity=2048 (TTFA p99 66 ms), or 96 at capacity=1024. Engine knobs, design notes and the conversion tools are in docs/ENGINE.md. The text normaliser is described in orqanta_voice/text/README.md.

Limitations

  • Assamese is the weakest language, with the highest CER and the least stable voice identity. No voice has much Assamese training audio.
  • Very short prompts (1-2 words) can drift in voice identity. Prefer a slightly longer phrase for short agent turns.
  • Code-mixed and mixed-script text has the highest error rates, and English words inside Indic sentences vary by voice.
  • URLs, symbols and long digit strings need the normaliser (on by default in the server, normalize=True in Python).
  • Clone similarity is recognisably close but not identical. Noisy or very short references reduce it.
  • Inline emotion tags ([laughs], [whispers], ...) are best effort.
  • Sampling. Output is sampled. The same seed is reproducible only when the request runs alone.

Responsible use

Do not use Orqanta-Voice to impersonate real people, to clone a voice without the speaker's consent, for fraud, or to defeat voice authentication. Tell listeners when speech is synthetic. To report misuse or a security problem, see SECURITY.md (contact: 117009786+GANDHIKALASI@users.noreply.github.com).

Repository layout

path content
orqanta_voice/ public API (api.py), streaming engine (engine.py), HTTP/WS server (server.py), client, guards, text normaliser, tools, tests
serve/ CUDA-graph components: fused backbone step, fp16 depth decoder, one-frame Mimi decoder, KV cache
tts/ model definition and the training-time prompt packer the engine reproduces
scripts/ prompt and stop-control helpers shared with the model code
configs/ model config and the duration prior read by the engine
examples/ command-line synthesis, OpenAI client, WebSocket streaming, voice cloning
docs/ENGINE.md engine internals, knobs, memory and latency measurements, checkpoint conversion

Tests

The CPU tests need no GPU and no weights:

pip install -e ".[dev]" --extra-index-url https://download.pytorch.org/whl/cu128
./run_tests.sh            # = CUDA_VISIBLE_DEVICES= python -m pytest -q orqanta_voice/tests/test_text.py orqanta_voice/tests/test_guards.py orqanta_voice/tests/test_server.py

The GPU checks (orqanta_voice/tests/test_backbone_*.py, test_depth_fused.py, test_rope_kernel.py, test_sampling.py) are scripts that take a checkpoint path. See their docstrings.

Author & Maintainer

License

Apache-2.0. See LICENSE. The model weights have their own license on the Hugging Face model card. Orqanta-Voice builds on Qwen3, Mimi (Kyutai) and SpeechBrain ECAPA-TDNN; see their licences.

Citation 

@misc{orqantavoice,
  title        = {Orqanta-Voice: Streaming Multilingual Text-to-Speech for Indic Languages},
  author       = {Kalasi, Gandhi},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/buggandhi/Orqanta-Voice}}
}

GitHub's "Cite this repository" button reads CITATION.cff. Changes are listed in CHANGELOG.md.

Downloads last month
-
Inference Providers NEW
Text-to-Speech
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support