Step-Audio Chat
Step-Audio Chat is the 130B multimodal language component of Step-Audio. It brings speech recognition, meaning, dialogue control, voice cloning and speech generation into one model component.
Account for the audio components
The repository identifies these weights as the language-model component. A working speech system also needs the release's audio processing and waveform path.StepFun Step-Audio-Chat model card
Plan beyond the weight download
Practical guidance. This model is useful for research into a large end-to-end speech system. Estimate memory for the full pipeline, not only the language component. For a smaller adaptation project, compare Step-Audio 2 Mini.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Step-Audio-Chat |
| Parameters | 130 billion.StepFun Step-Audio-Chat model card |
| License | Apache 2.0 is declared on the model card.StepFun Step-Audio-Chat model card |
Related models
- Step-Audio 2 Mini
StepFun · StepAudio 2
A speech-dialogue model supporting sound understanding, tool calls and retrieval from text and acoustic material.
Launch date not confirmedAPI · Downloadable - Step-Audio AQAA
StepFun · Step-Audio
A 130B audio-language model that generates spoken answers directly from audio input.
Launch date not confirmedResearch releaseDownloadable - Step-Audio TTS 3B
StepFun · Step-Audio
Step-Audio TTS 3B uses a dual-codebook language-model design for speech synthesis.
Launch date not confirmedDownloadable