wowsuch ai
Live

Edge0Model

Audio8-TTS-Realistic-0.6B

Audio8-TTS-Realistic-0.6B is a 601-million-parameter text-to-speech model that builds on Audio8-TTS-Preview-0.6b. It supports 23 languages and zero-shot voice cloning, and includes its codec, tokenizer, processor, and custom Transformers code.

What it does

Use it to generate speech from text, with or without a reference recording, or to clone a voice from a reference recording and transcript.

Availability
Complete model checkpoint and interactive Playground are available
Pricing model
Not established
Deployment
Transformers inference; SGLang Omni GPU serving adapter
Privacy
Not established
Licence
Apache-2.0
Capability
audio generation
Modality
textaudio
Access
open weightswebAPI
Deployment
on-premiseshosted
Pricing
unknown
Target user
developercreator

Evidence

6 claims
  • The model supports 23 languages, adding 12 languages compared with Preview. [1]
    This release supports **23 languages**, adding **12 languages compared with Preview**.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • It supports zero-shot voice cloning from a reference recording and transcript. [1]
    - **Flexible generation:** zero-shot voice cloning from a reference recording and transcript, or speech generation without a reference.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The repository includes the complete model checkpoint, codec, tokenizer, processor, and custom Transformers code. [1]
    This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The SGLang Omni adapter provides an OpenAI-compatible /v1/audio/speech service. [1]
    - **GPU serving:** an SGLang Omni adapter with paged attention, dynamic batching, and an OpenAI-compatible speech API.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The Playground is hosted on Hugging Face ZeroGPU, with availability depending on the queue and daily GPU allowance. [1]
    Hosted on Hugging Face ZeroGPU; availability depends on the queue and your daily GPU allowance.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is released under the Apache-2.0 license. [1]

Sources

1
1
Hugging FaceOwner-controlled
https://huggingface.co/Edge0/Audio8-TTS-Realistic-0.6b Retrieved 2026-11-01 00:56 UTC
Verified

Versions

1
VersionEffectiveChangeChanged fieldsState
12026-11-01 00:56 UTCpublicationNoneCurrent

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.