metadata
title: Audio8 TTS Preview 0.6B
colorFrom: red
colorTo: gray
sdk: docker
app_port: 7860
models:
- Audio8/Audio8-TTS-Preview-0.6b
license: apache-2.0
Audio8 TTS Preview 0.6B
Multilingual text-to-speech and zero-shot voice cloning for
Audio8/Audio8-TTS-Preview-0.6b.
The service uses the official Audio8 adapter with SGLang Omni 0.1.0 and
SGLang 0.5.8.
Reference audio uploaded through the web interface is limited to 30 seconds.
The A10G runtime enables torch.compile with SGLang's native batch policy and
uses CUDA Graph without an Audio8-specific compile batch-size limit.
Waveform decoding runs once after acoustic-token generation; incremental
waveform streaming is disabled for long-form stability.
API
curl -sS \
-H 'Content-Type: application/json' \
-d '{
"model": "audio8/tts-0.6b",
"input": "Audio8 generates this sentence with the reference voice.",
"response_format": "wav",
"temperature": 0.8,
"top_p": 0.95,
"top_k": 50,
"references": [{
"audio_path": "https://example.com/reference.wav",
"text": "The exact transcript spoken in the reference audio."
}]
}' \
https://audio8-audio8-tts-preview-0-6b.hf.space/v1/audio/speech \
-o audio8-clone.wav
Use reference voices only with the speaker's permission and disclose synthetic audio where appropriate.