AxolotlAudio AA-2

Multilingual neural text-to-speech from AxolotlAudio.

Runtime metadata ships as a compact bundle (assets/runtime.aa1). Use the bundled SDK to materialize weights.

Architecture

Component	Description
Backbone	Pretrained Qwen3-4B (~4B params) — text planning, long-context prosody, multilingual input
Acoustic head	Hybrid autoregressive module with multi-codebook RVQ (~400M params)
Codec	Neural codec (neural_codec.bin) for waveform reconstruction

The text stack reuses the Qwen3 tokenizer (chat template, extended audio token slots). That is intentional — we inherit Qwen3's multilingual coverage and instruction-following substrate rather than training a tokenizer from scratch.

Design influences

AA-2 integrates ideas from several open speech / TTS research lines (not a fork of any single repo):

Project	What we took
VITS2	End-to-end vocoder-less training philosophy
Bert-VITS2	Multilingual BERT-style text side-conditioning
GPT-SoVITS	Two-stage text → semantic → acoustic decomposition
MQTTS	Multi-quantizer acoustic token modeling
GPT-Fast	Fast secondary AR stack for residual codebooks at inference
Qwen3	LLM backbone + tokenizer substrate

Usage

from axolotl_audio import load_bundle

model = load_bundle("AxolotlAudio/aa-2")

Delivery markup

<soft> Can you hear me clearly?
<energetic> That sounds great!

License

Proprietary AxolotlAudio weights.