AU
Audio8
Speech model ·Jul 2026

Audio8 TTS Preview 0.6B

Speech Open Source
601.2M
Parameters
2K
Context

About Audio8 TTS Preview 0.6B

Audio8 TTS Preview 0.6B is an AI model developed by Audio8, in the speech category, released in 2026, made available as an open-source model with 0.6B params. Audio8's TTS Preview 0.6B is a SOTA-class multilingual text-to-speech model with zero-shot voice cloning. 0.6B parameters, competitive with much larger models on Seed-TTS benchmarks. 44.1 kHz output with integrated codec.

On this page you'll find Audio8 TTS Preview 0.6B's full specifications, including a context window of 2K tokens. Review provider pricing and benchmark scores below, or compare Audio8 TTS Preview 0.6B head-to-head with other speech models.

→ More models by Audio8 → All speech models → AI benchmarks leaderboard

Run Audio8 TTS Preview 0.6B locally — what fits

GPUs with enough VRAM to hold Audio8 TTS Preview 0.6B at FP16 (lower precision needs less), from best value to most headroom. Generation speed depends on your tool, resolution and step count, so we don't estimate it.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
12 GB VRAM
fits at FP16 · ~8.3 GB headroom
See fit detail →
Best
AMD Instinct MI455X
Consumer GPU · price n/a
432 GB VRAM
fits at FP16 · ~394.7 GB headroom
See fit detail →

VRAM fit only — we don't estimate generation speed for image/video/audio models (it depends on the tool, resolution and steps).

Consumer GPU
39 options that fit
→
Apple
23 options that fit
→
Datacenter GPU
13 options that fit
→

Community

Would you run Audio8 TTS Preview 0.6B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Audio8 TTS Preview 0.6B

AI
OuteTTS-0.1-350M
· 350M
 AI
SeedLLM
· 7B
 AI
Weight Decay
· 8.4K
 AQ
Qwen Audio 3.0 TTS
Alibaba Qwen
 AS
GigaAM Multilingual
ai-sage
 NY
CrisperWhisper 2.0
Nyralabs

Frequently asked questions

What is Audio8 TTS Preview 0.6B? ▶

Audio8's TTS Preview 0.6B is a SOTA-class multilingual text-to-speech model with zero-shot voice cloning. 0.6B parameters, competitive with much larger models on Seed-TTS benchmarks. 44.1 kHz output with integrated codec. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Audio8 TTS Preview 0.6B? ▶

Audio8 TTS Preview 0.6B was developed by Audio8 and released in 2026.

Is Audio8 TTS Preview 0.6B open source or proprietary? ▶

Audio8 TTS Preview 0.6B is released as open source — its weights are publicly available to download, run locally and fine-tune.

What is Audio8 TTS Preview 0.6B's context window? ▶

Audio8 TTS Preview 0.6B supports a context window of 2K tokens, and has 0.6B params.

How much does Audio8 TTS Preview 0.6B cost? ▶

Pricing for Audio8 TTS Preview 0.6B depends on the provider. See the providers table on this page for the latest API rates.

How does Audio8 TTS Preview 0.6B perform on benchmarks? ▶

Benchmark scores for Audio8 TTS Preview 0.6B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

Audio8 TTS 0.6B Local Install Guide | FREE Multilingual AI Text-to-Speech + Voice Cloning (2026)

Know a great video about Audio8 TTS Preview 0.6B?