Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer uses AI to improve video quality, restore details, reduce blur, and upscale videos to 8K.
LiteRT / TensorFlow Lite port of
openbmb/VoxCPM2
— a 2B-parameter multilingual diffusion-autoregressive TTS model with
48 kHz
studio-quality output, voice cloning, and instruction-driven voice design.
This bundle ships the model as
four separate LiteRT graphs
plus a manifest. The on-device worker is expected to orchestrate the loop:
text_prefill ─► token_step (×N) ─► audio_decode
Reference audio is encoded once via
audio_encoder
. The K/V cache for the LM and residual decoder is owned by the host worker (not mutated inside the graph), which lets the runtime own retry / idempotency semantics.
Status:
experimental. The
token_step
graph depends on
litert_torch
static K/V-cache lowering; integrators should validate numerical parity end-to-end before relying on this bundle in production.
Capabilities
30 languages
including English, Chinese, Indonesian, Japanese, Korean
48 kHz output
Zero-shot synthesis
— generate speech from text alone
Voice cloning
— clone a target speaker from a single reference clip
Voice design
— natural-language style control (e.g.
"young female voice, warm and gentle"
)
Ultimate cloning
— reference audio + transcript for prosody-preserving cloning
Files
File
Variant
Role
voxcpm2-text-prefill.tflite
INT8 weights / FP32 activations
Encode text + (optional) reference-audio prefix into LM hidden states, residual hidden, prefix feature conditioning, and the initial K/V caches.
voxcpm2-token-step.tflite
INT8 weights / FP32 activations
One AR step. Takes current LM / residual hidden, conditioning, K/V cache and position id. Emits the next predicted feature, stop logits, updated hidden states, and updated K/V cache.
voxcpm2-audio-encoder.tflite
FP32
Encode a reference clip (16 kHz PCM) into the patch features that condition the prefill.
voxcpm2-audio-decoder.tflite
FP32
Decode latent → 48 kHz PCM via the upstream AudioVAE.
Upstream tokenizer source (kept for parity with the HF model).
The conv-heavy encoder and decoder are intentionally kept FP32 — the
dynamic_wi8_afp32
recipe does not lower the conv kernels that VoxCPM2's AudioVAE relies on, and quantising the vocoder has historically been audible-risky.
Default decoding parameters
Parameter
Default
max_text_tokens
(context)
512
max_generated_tokens
2048
inference_timesteps
(CFM)
10
cfg_value
2.0
Sample rate (output)
48 000 Hz
Sample rate (audio conditioning)
16 000 Hz
These mirror the host-side defaults exposed in
config.json
; runtimes are free to override them.
Token-step cache contract
The token-step graph takes and returns the LM and residual K/V cache as explicit inputs/outputs. Cache layout:
Apache 2.0 (inherited from upstream openbmb/VoxCPM2).
Responsible use
Voice cloning capability is included. Users are responsible for obtaining consent for any voice that is cloned and for not using the model to impersonate individuals without their permission, generate disinformation, or commit fraud.
Runs of aufklarer VoxCPM2-LiteRT on huggingface.co
83
Total runs
0
24-hour runs
83
3-day runs
83
7-day runs
83
30-day runs
More Information About VoxCPM2-LiteRT huggingface.co Model
VoxCPM2-LiteRT huggingface.co is an AI model on huggingface.co that provides VoxCPM2-LiteRT's model effect (), which can be used instantly with this aufklarer VoxCPM2-LiteRT model. huggingface.co supports a free trial of the VoxCPM2-LiteRT model, and also provides paid use of the VoxCPM2-LiteRT. Support call VoxCPM2-LiteRT model through api, including Node.js, Python, http.
VoxCPM2-LiteRT huggingface.co is an online trial and call api platform, which integrates VoxCPM2-LiteRT's modeling effects, including api services, and provides a free online trial of VoxCPM2-LiteRT, you can try VoxCPM2-LiteRT online for free by clicking the link below.
aufklarer VoxCPM2-LiteRT online free url in huggingface.co:
VoxCPM2-LiteRT is an open source model from GitHub that offers a free installation service, and any user can find VoxCPM2-LiteRT on GitHub to install. At the same time, huggingface.co provides the effect of VoxCPM2-LiteRT install, users can directly use VoxCPM2-LiteRT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.