Gated, non-commercial (CC BY-NC 4.0): ask for access on this page. Cilla Lite is the small 6-layer model for CPUs, distilled from Cilla with guidance baked in (one pass per frame). It speaks Persian in the voice of a short audio prompt. Built on Pocket TTS by Kyutai.
Alternatives to cilla-lite
120 open-weight models that do the same job as cilla-lite (110M TTS), ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.
601MApache 2.024K 534Oct 2026- Same category
- Larger (601M vs 110M)
- Commercial use OK
This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.
601MApache 2.024K 534Oct 2026- Same category
- Larger (601M vs 110M)
- Commercial use OK
ⓍTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. There is no need for an excessive amount of training data that spans countless hours.
467Mcoqui-public-model-license5M 4KOct 2023- Same category
- Larger (467M vs 110M)
- Widely used
Magenta RealTime 2 is offered under a combination of licenses: the codebase is licensed under Apache 2.0, and the model weights under Creative Commons Attribution 4.0 International. In addition, we specify the following usage terms:
?BCC BY 4.018.3K 267May 2026- Same category
- Commercial use OK
The most accurate open Vietnamese TTS we know of — 4× fewer word errors than the next best model, and it runs faster than real time on a laptop CPU.
?BMIT7.9K 55Aug 2026- Same category
- Commercial use OK
Gepard is a text-to-speech model built for real-time conversation. It starts speaking the moment text begins arriving, generating audio piece by piece instead of waiting for a full sentence — so it feels like a live voice, not a recording.
556M256K ctx Apache 2.010.8K 134Jun 2026- Same category
- Larger (556M vs 110M)
- Commercial use OK
Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations
370M125K ctx lfm1.0784 183Feb 2026- Same category
- Larger (370M vs 110M)
If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!
?Bterattsv2-openrail-m-commercial-attribution4K 38Aug 2026- Same category
This repository contains the English (eng) language text-to-speech (TTS) model checkpoint.
36MCC BY-NC 4.053.3K 184Aug 2023- Same category
- Smaller (36M vs 110M)
Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations
370M125K ctx lfm1.0304 43Feb 2026- Same category
- Larger (370M vs 110M)
Fun-CosyVoice 3.0 is an advanced text-to-speech (TTS) system based on large language models (LLM), surpassing its predecessor (CosyVoice 2.0) in content consistency, speaker similarity, and prosody naturalness. It is designed for zero-shot multilingual speech synthesis in the wild.
500MApache 2.015.2K 99Jul 2025- Same category
- Larger (500M vs 110M)
- Commercial use OK
Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.
915MApache 2.0839.5K 374Jan 2026- Same category
- Larger (915M vs 110M)
- Commercial use OK
Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.
906MApache 2.0715.7K 212Jan 2026- Same category
- Larger (906M vs 110M)
- Commercial use OK
A complete voice. A smaller footprint. Six English voices. Local generation. More ways to make speech your own.
?BApache 2.0805 47Nov 2026- Same category
- Commercial use OK
Audio8 TTS Preview supports multilingual speech generation and zero-shot voice cloning. This repository contains the complete checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and Hugging Face remote code.
601MApache 2.03.8K 435Jul 2026- Same category
- Larger (601M vs 110M)
- Commercial use OK
AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language…
?BMIT1.4K 396Aug 2026- Same category
- Commercial use OK
IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
?BUnknown licence26K 796Jun 2025- Same category
Marvis is a cutting-edge conversational speech model designed to enable real-time streaming text-to-speech synthesis. Built with efficiency and accessibility in mind, Marvis addresses the growing need for high-quality, real-time voice synthesis that can run on consumer devices such as Apple…
368MApache 2.0248 29Oct 2025- Same category
- Larger (368M vs 110M)
- Commercial use OK
A high-speed, high-fidelity Text-to-Speech model optimized for real-time conversational AI applications.
370M125K ctx lfm1.0322 166Sept 2025- Same category
- Larger (370M vs 110M)
VoxCPM is a novel tokenizer-free Text-to-Speech (TTS) system that redefines realism in speech synthesis. By modeling speech in a continuous space, it overcomes the limitations of discrete tokenization and enables two flagship capabilities: context-aware speech generation and true-to-life zero-shot…
500MApache 2.05.2K 830Sept 2025- Same category
- Larger (500M vs 110M)
- Commercial use OK
VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.
2.3BApache 2.0971.2K 1.8KApr 2026- Same category
- Larger (2.3B vs 110M)
- Commercial use OK
AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language…
?BMIT664 107Aug 2026- Same category
- Commercial use OK
This repository contains the model as described in LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM.
30MCC BY-NC-SA 4.01.9K 58Mar 2025- Same category
- Smaller (30M vs 110M)
E2-TTS is an open-weight tts model from SWivid, published on Hugging Face.
?BCC BY-NC 4.083.2K 57Oct 2024- Same category