SSyncDev

AI model comparison

neuphonic/neucodec-onnx-decoder vs neuphonic/neucodec-onnx-decoder-int8

Compare pricing, context limits, supported inputs and deployment options to choose a model for your workflow.

Two exports for the same audio-decoding stage

Both artifacts decode compatible NeuCodec codes into audio. One is an ONNX export; the other is quantized to INT8. Neither is a complete text-to-speech model, and neither replaces the encoder or the model that supplies speech codes.

Read the recorded specifications

The table below shows each profile's documented interface and recorded limits. Missing prices or measurements remain unknown. Open the source links on each profile to confirm the current checkpoint or API route.

Side-by-sideCapabilities and practical differences

neuphonic

neuphonic/neucodec-onnx-decoder

The NeuCodec ONNX decoder converts compatible NeuCodec codes into an audio waveform. It is an exported decoder, not a complete text-to-speech model.

Accepts

  • Audio codes input

Produces

  • Audio output
Full model profileModel card on Hugging Face ↗
VS

neuphonic

neuphonic/neucodec-onnx-decoder-int8

The NeuCodec INT8 ONNX decoder converts compatible NeuCodec codes into an audio waveform. It is an exported decoder, not a complete text-to-speech model.

Accepts

  • Audio codes input

Produces

  • Audio output
Full model profileModel card on Hugging Face ↗

Specifications

Pricing, limits and capabilities

Specifications for neuphonic/neucodec-onnx-decoder and neuphonic/neucodec-onnx-decoder-int8. Higher limits and lower prices describe these figures only.
Specificationneuphonic/neucodec-onnx-decoderneuphonic/neucodec-onnx-decoder-int8
Providerneuphonicneuphonic
Listed pricing routeneuphonicneuphonic
Model family——
Accepted inputsaudio codesaudio codes
Produced outputsaudioaudio
Reasoning modeNot documentedNot documented
Tool callingNot documentedNot documented
Image inputNot documentedNot documented
Audio inputNot documentedNot documented
Structured outputNot documentedNot documented
LicenseApache-2.0Apache-2.0

Workload guidance

Which model should you choose?

A useful decision test

Run the same encoded clips through both exports on the intended device. Listen for artifacts, missing detail and level changes, and measure end-to-end latency including buffer conversion. Use the smaller export when it meets your audio-quality threshold; an INT8 label alone does not prove faster execution on every device.

Inspect the first model profile and the second model profile. Keep your test inputs, runtime settings and acceptance criteria with the result so the comparison can be repeated.

Documentation and model profiles

Explore each model’s features, API requirements and licence terms in the sources below.

Questions people ask

It brings together documented inputs and outputs, token limits, deployment terms and available pricing. When both models have source-linked, verified results on a shared benchmark, those results are shown with their individual sources. The comparison is a starting point for evaluating your own workload.

Compare a different pair

Search by model or provider to explore another comparison.

Open model comparison