OmniVoice is a massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it delivers high-quality speech with superior inference speed, supporting voice cloning and voice design.
Audio8-TTS-Realistic-Air
Edge0·released 14 Oct 2026
hf download Edge0/Audio8-TTS-Realistic-AirThis 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.
How much VRAM does Audio8-TTS-Realistic-Air need?
At FP16 / BF16 Audio8-TTS-Realistic-Air needs about 1.8 GB of GPU memory.
| Quantisation | Total |
|---|---|
| 4-bitRecommended default for local use | ≈0.9 GB |
| 8-bitLossless in practice, twice the size of Q4 | ≈2.2 GB |
| FP16 / BF16recommendedFull precision, as released | ≈1.8 GB |
Estimates for the weights plus runtime overhead; activations vary with resolution and batch size. Pick a GPU above and the fit column checks every row against it. Weights marked “file” use the real GGUF download size; “est.” rows are computed from the parameter count.
Run Audio8-TTS-Realistic-Air locally
These commands load the original weights from Hugging Face.
from transformers import pipeline
pipe = pipeline("text-to-speech", model="Edge0/Audio8-TTS-Realistic-Air")
result = pipe("Self-hosting puts you in control of your data.")
print(result)Quantised versions and downloads
| Repository | Format | Quant | Size |
|---|---|---|---|
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q8_0 | 1.5 GB |
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q2_K | 1.7 GB |
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q3_K | 1.7 GB |
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q3_K_S | 1.7 GB |
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q4_K | 1.7 GB |
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q4_K_S | 1.7 GB |
| Hansda/Audio8-TTS-Realistic-Air-GGUF | GGUF | Q6_K | 1.7 GB |
| loom-ai-org/audio8-tts-realistic-0.6b-loom | GGUF | — | — |
| groxaxo/Audio8-TTS-Realistic-Air-MLX8-Selective | MLX | — | — |
| ShinePixelOrg/Audio8-TTS-Realistic-Air-MLX-Codec-Q8 | MLX | — | — |
About Audio8-TTS-Realistic-Air
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. Try speech generation and voice cloning in the interactive Playground. Hosted on Hugging Face ZeroGPU; availability depends on the queue and your daily GPU allowance. • Improved realism: more natural prosody and expressive delivery, building on Preview. • Broader multilingual coverage: 23 languages, including 12 additions to Preview's 11 supported languages. • Compact model: 601 million main-model parameters, with the audio codec bundled separately. • Flexible generation: zero-shot voice cloning from a reference recording and transcript, or speech generation without a reference. • GPU serving: an SGLang Omni adapter with paged attention, dynamic batching, and an OpenAI-compatible speech API. Note: Language quality varies; see the per-language evaluation below. Benchmark coverage includes some additional languages and is distinct from the supported-language list. Audio8 TTS uses a DualAR architecture inspired by Fish Audio S2 Pro. The slow AR transformer predicts one semantic token for each audio frame. The fast AR transformer predicts the frame's codec codebooks, conditioned on the slow hidden state and preceding codebooks.
Full model card on Hugging Face →Alternatives to Audio8-TTS-Realistic-Air
All alternatives →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.
Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages.
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.
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.
Qwen3-TTS is a series of advanced multilingual, controllable, robust, and streaming text-to-speech models developed by the Qwen team.
Audio8-TTS-Realistic-Air FAQ
- How much VRAM does Audio8-TTS-Realistic-Air need?
- About 1.8 GB at FP16 / BF16.
- Can Audio8-TTS-Realistic-Air run on the RTX 4060?
- Yes. It fits at FP16 / BF16 (about 1.8 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.
- Can I use Audio8-TTS-Realistic-Air commercially?
- Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.
- How do I run Audio8-TTS-Realistic-Air locally?
- It runs with Transformers. Each has copy-paste examples in its docs.
Rate this model
Data from Hugging Face, the model card and public leaderboards. Memory and speed figures are estimates; real numbers depend on the runtime, context length and drivers. Always check the licence yourself before commercial use.
0 comments