> ## Content Index
> Fetch the complete content index at: https://globalfeed.ai/llms.txt
> Use this file to discover other available public pages before exploring further.

# OmniVoice: open source text-to-speech and voice cloning for 600+ languages, 40 times faster than real time
- URL: https://globalfeed.ai/en/omnivoice-open-source-text-to-speech-and-voice-cloning-for-600-languages-40-times-faster-than-real-time/
- Published: 2026-09-08T20:11:53.000Z
- Updated: 2026-09-08T20:11:53.000Z
- Description: The Next-gen Kaldi team has released OmniVoice under Apache-2.0: zero-shot speech in more than 600 languages, cloning from a sample, and a real-time factor of 0.025. The repository has passed 10,700 stars.
- Author: GlobalFeed Editor
- Tags: OmniVoice, k2-fsa, Next-gen Kaldi, text to speech, open source model, x-yok, dil-en, elle, video

The **Next-gen Kaldi** team has released **OmniVoice**, a text-to-speech model, under the **Apache-2.0** licence. The project describes itself as a state-of-the-art massively multilingual zero-shot text-to-speech model and claims support for **more than 600 languages**. The GitHub repository has passed 10,700 stars and 1,700 forks.

## Two capabilities: cloning and design

The model does two separate jobs. The first is **voice cloning**: it reproduces a voice from a sample you supply. The second is **voice design**: it produces a voice with the characteristics you ask for, without a sample. Zero-shot operation is part of the same picture, meaning no extra training is needed for a language or a voice the model has not heard before.

## Speed

The repository gives a real-time factor of **0.025**. One second of audio takes roughly 0.025 seconds to generate, which is 40 times faster than real time. With FlashInfer acceleration the project reports up to a 2.6x further speedup, reaching an RTF of **0.0115** at batch size 8\. These are the project's own measurements; no independent evaluation has been published.

## Who is behind it

k2-fsa runs **Next-gen Kaldi**, the successor to Kaldi, a long-standing name in speech processing. **sherpa-onnx**, from the same organisation, has 14,700 stars and runs speech-to-text, text-to-speech, speaker diarization and voice activity detection with no internet connection, supporting embedded systems, Android, iOS, HarmonyOS, Raspberry Pi and several NPU targets. What is on offer is therefore more than a single model: it is a stack already used to running on device.

## For comparison

[Inworld TTS-2, which we covered on 2 September](https://globalfeed.ai/en/inworlds-realtime-tts-2-goes-live-100-ms-voice-and-one-identity-across-200-languages/), holds one voice identity across more than 200 languages and is offered as a commercial service. OmniVoice sits somewhere else: three times the language count, an Apache-2.0 licence, and downloadable weights, which means generation can stay on your own hardware. Language count and quality per language are different things; 600 is the number of supported languages, not a promise of equal quality in each.

Source: [github.com/k2-fsa/OmniVoice](https://github.com/k2-fsa/OmniVoice?ref=globalfeed.ai).