Step-Audio-Chat 130B

Training compute

1.9×10²⁴ FLOP

Parameters

130B

Published

Feb 18, 2025

Step-Audio-Chat 130B is an AI model developed by StepFun (China), first published in February 2025. It works in the speech domain, on tasks such as speech synthesis, speech recognition (asr), speech-to-text and 4 more.

Training it took an estimated 1.9×10²⁴ FLOP of compute (estimation method: operation counting). The model has 130,000,000,000 parameters. It was trained on roughly 1.7T datapoints.

Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Step-1. Epoch AI rates the confidence of this record as confident.

Full record

Organization: StepFun
Country of organization: China
Domain: Speech
Task: Speech synthesis, Speech recognition (ASR), Speech-to-text, Text-to-speech (TTS), Audio question answering, Audio generation, Speech-to-speech
Training compute: 1.9×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 130,000,000,000
Dataset size: 1.7T
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Base model: Step-1
Epoch confidence: Confident