on-device iOS client · MOSS-TTS-Nano (ONNX for iOS / macOS)
On-device text-to-speech assets derived from OpenMOSS-Team/MOSS-TTS-Nano-100M and OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano.
This repo bundles everything the on-device iOS / macOS client needs to synthesize speech without any server component:
- Split ONNX graphs (LM + audio decoder) exported with practical fixed shapes (see
onnx/onnx_shapes.json). - The original SentencePiece tokenizer (
tokenizer.model) plus a 1:1 verified fasttokenizer.jsonforswift-transformers. - The upstream
config.json, exposing all token IDs and model-side constants used by the prompt builder.
Repo layout
.
├── onnx/
│ ├── moss_tts_nano_lm_fp32.onnx # ~490 MiB — use on macOS (CoreML EP) / Mac-class iPad
│ ├── moss_tts_nano_lm_fp16.onnx # ~250 MiB — default for iPhone
│ ├── moss_tts_nano_decode_fp32.onnx # ~62 MiB
│ ├── moss_tts_nano_decode_fp16.onnx # ~32 MiB
│ └── onnx_shapes.json # prompt_len / frames / sample rate / special tokens
├── tokenizer/
│ ├── tokenizer.json # fast tokenizer (BPE + byte fallback) verified 1:1 against SPM
│ ├── tokenizer.model # original SentencePiece model
│ ├── tokenizer_config.json
│ └── special_tokens_map.json
└── config/
└── config.json # upstream MOSS-TTS-Nano config
Fixed shapes (baked into the ONNX graphs)
| field | value | meaning |
|---|---|---|
prompt_len |
512 | Max prompt_input_ids rows (text tokens + MOSS template overhead). Pad/truncate per chunk. |
n_vq |
16 | Number of audio codebooks. |
n_vq_plus_one |
17 | Columns in prompt_input_ids (1 text column + 16 audio codebook columns, all set to audio_pad_token_id at the text-only prompt stage). |
max_new_frames |
32 | Frames the LM can emit per invocation. |
max_audio_samples |
1,920,000 (≈ 40 s @ 48 kHz) | Upper bound on the decoder output length. |
sample_rate |
48,000 Hz | Output WAV sample rate. |
channels |
2 | Stereo output. |
Long inputs must be split into prompt-budget-sized chunks in the client (sentence-aware, with a single MOSS prompt overhead per chunk) and the resulting WAV segments concatenated. The on-device iOS package does this via MossTTSNanoTextChunker.
Runtime contract (on-device iOS / macOS client)
- Build
prompt_input_ids/attention_maskon-device using the fasttokenizer.json(no server roundtrip).- See
MossTTSNanoPromptBuilder— Swift port ofMossTTSNanoForCausalLM.build_inference_input_ids(mode="continuation"). - Pads / truncates to
prompt_len = 512and fills audio codebook columns withaudio_pad_token_id.
- See
- Run
moss_tts_nano_lm_*.onnxto produceaudio_codesof shape[1, max_new_frames, n_vq]. - Run
moss_tts_nano_decode_*.onnxon a sliding window of frames to obtain raw 48 kHz stereo PCM. - Concatenate segment WAVs for multi-chunk inputs.
Export provenance
Exported via Notebooks/MOSS_TTS_Nano/export_moss_tts_nano_e2e_onnx.py (torchscript backend, opset 17) with:
python export_moss_tts_nano_e2e_onnx.py \
--mode split \
--prompt-len 512 \
--max-new-frames 32 \
--max-audio-samples 1920000 \
--write-shapes-json
FP16 graphs produced with onnxconverter_common.float16.convert_float_to_float16(keep_io_types=False).
Token IDs in onnx_shapes.json reflect the upstream config at export time (OpenMOSS-Team/MOSS-TTS-Nano-100M commit 44502f80).
License
Apache-2.0, same as the upstream MOSS-TTS-Nano-100M and MOSS-Audio-Tokenizer-Nano releases.
Acknowledgements
Thanks to the OpenMOSS team for releasing the MOSS-TTS-Nano and MOSS-Audio-Tokenizer-Nano weights under a permissive license that makes on-device deployment feasible.
Model tree for aoiandroid/moss-tts-nano-onnx-fp32
Base model
OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano