A full fine-tune of OpenMOSS's MOSS-TTS-v1.5 (8B parameters, Qwen3-8B backbone, moss_tts_delay architecture, 32-codebook audio @ 24 kHz), specialised for expressive voice acting.

The fine-tune pushes the base model toward:

Emotional delivery — happy, sad, angry, fearful, tender, sarcastic, whispered, shouted, and everything in between.
Character voices — distinct personas driven from a natural-language instruction.
Voice cloning — clone a speaker's timbre and delivery style from a short reference clip.

Sibling model: the 4.55-billion-parameter local-transformer variant at 48 kHz — laion/moss-tts-local-transformer-4.55b-voice-acting (merged, off-the-shelf).

	this model — 8B delay	4.55B local transformer
audio tokenizer	`MOSS-Audio-Tokenizer` (v1) — 24 kHz mono	`MOSS-Audio-Tokenizer-v2` — 48 kHz
output	24 kHz (optionally bandwidth-extended with Sidon)	native 48 kHz, use raw
strengths	larger capacity, broad multilingual coverage	higher audio bandwidth out of the box, smaller/faster, measured higher word accuracy on identical prompts (invWER 0.97 vs 0.83)

It keeps the multilingual coverage of the base model (English, German, Chinese, and many more — see the language list), and is fully API-compatible with MOSS-TTS-v1.5: same processor, same generate interface, same input schema.

Model at a glance


Base model	OpenMOSS-Team/MOSS-TTS-v1.5
Architecture	`moss_tts_delay` (delay-pattern TTS LM)
Backbone	Qwen3-8B
Parameters	~8B (full fine-tune, no adapters)
Audio codec	32-codebook RVQ, 24 kHz — `OpenMOSS-Team/MOSS-Audio-Tokenizer` (v1, mono)
Precision	bfloat16
License	Apache-2.0

Prompting

The model is prompted through the processor's native build_user_message fields:

instruction — how to say it: the emotion, character, or performance direction (e.g. "Speak like a weary old sailor telling a ghost story, low and gravelly.").
text — what to say: the words to be spoken.
language — the language of text (e.g. "English", "German", "Chinese"). Set it whenever the language is known; it improves multilingual stability.
reference — optional audio (a file path, URL, or waveform tensor) to clone a voice. Omit it to let the model invent a voice consistent with the instruction.

Usage

python

from transformers import AutoModel, AutoProcessor
import torch, torchaudio

# Recommended SDPA backend settings (the cuDNN SDPA path is broken for this model)
torch.backends.cuda.enable_cudnn_sdp(False)
torch.backends.cuda.enable_flash_sdp(True)
torch.backends.cuda.enable_mem_efficient_sdp(True)
torch.backends.cuda.enable_math_sdp(True)

model_id = "laion/moss-tts-v1.5-8b-voice-acting"
device, dtype = "cuda", torch.bfloat16

processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
processor.audio_tokenizer = processor.audio_tokenizer.to(device)

model = AutoModel.from_pretrained(
    model_id,
    trust_remote_code=True,
    dtype=dtype,
    attn_implementation="sdpa",   # or "flash_attention_2" if installed
).to(device).eval()

def synth(message, out_path):
    batch = processor([[message]], mode="generation")
    with torch.no_grad():
        outputs = model.generate(
            input_ids=batch["input_ids"].to(device),
            attention_mask=batch["attention_mask"].to(device),
            max_new_tokens=4096,
        )
    audio = processor.decode(outputs)[0].audio_codes_list[0]
    torchaudio.save(out_path, audio.unsqueeze(0).cpu().float(),
                    processor.model_config.sampling_rate)

# 1) Expressive delivery, model invents a voice (no reference)
synth(processor.build_user_message(
    instruction="Excited and breathless, like sharing amazing news with a best friend!",
    text="You will not believe what just happened. We actually did it!",
    language="English",
), "invented_voice.wav")

# 2) Voice cloning — clone the timbre/style of a reference clip
synth(processor.build_user_message(
    instruction="Calm, warm, reassuring bedtime-story narrator.",
    text="Once upon a time, in a quiet little village, everyone slept soundly.",
    language="English",
    reference=["/path/to/reference.wav"],
), "cloned_voice.wav")

processor.decode(...) returns a list of messages; each carries the decoded waveform in message.audio_codes_list[0] at processor.model_config.sampling_rate (24 kHz).

Sampling settings. A grid search over temperature and audio repetition penalty (scored for intelligibility, quality, and genuineness on a held-out English + German set) gives good defaults of temperature 1.0, repetition penalty 1.1 with a reference clip, and temperature 0.8, repetition penalty 1.1 without a reference. See GENERATION_SETTINGS.md for the full results table and per-metric best configs.

Training

This model was fine-tuned on a mix of the Emolia corpus and synthetic speech generated by several TTS models — primarily Gemini-3.1 TTS and DramaBox TTS. The goal of the mix was to concentrate on expressive, emotional, and character-driven delivery while preserving the base model's multilingual and voice-cloning abilities. It is a conservative full fine-tune: the base model's general capabilities are largely retained.

Tips

Put performance cues in instruction. Emotion, character, pacing, and vocal-burst / performance cues (laughter, sighs, gasps, whispering, shouting) belong in instruction, not in text.
German text: write it naturally. Use lowercase with proper umlauts (ä ö ü, not ae/oe/ue) and avoid ALL-CAPS, which the model tends to mispronounce. Reserve capitals for normal sentence casing.
Use punctuation for emphasis and prosody. !, ?, ., and ... meaningfully shape intonation and pauses — lean on them instead of capitalisation.
Set language whenever you know it; it stabilises multilingual synthesis.
Data augmentation. Voice cloning combined with text paraphrase is an effective way to generate additional, style-consistent training material.

Limitations

This is a conservative full fine-tune. It broadens expressive and voice-acting behaviour, but it may not beat task-specific baselines on every axis (e.g. raw intelligibility, speaker similarity, or a single narrow language/domain).
Expressiveness is driven by the instruction field; vague or contradictory instructions can produce inconsistent delivery. Iterate on wording.
As with any generative TTS, outputs should not be used to impersonate real individuals without consent. Use responsibly.

License

Released under the Apache-2.0 license.