StepFun: stepaudio-2.5-chat

About stepaudio-2.5-chat

StepFun StepAudio 2.5 Chat — end-to-end speech understanding that takes audio or text in and returns text, reading paralinguistic signal such as hesitation and laughter from the waveform itself rather than from a transcript. Supports persona customization across character, speech habits, and emotional range; audio is supplied as input_audio content parts on chat completions. For spoken replies use a TTS model.

Quickstart

Copy-paste API request.

curl -X POST https://api.chinaapi.ai/v1/chat/completions \
  -H "Authorization: Bearer $CHINAAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stepaudio-2.5-chat",
    "messages": [
      {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["CHINAAPI_API_KEY"],
    base_url="https://api.chinaapi.ai/v1",
)

response = client.chat.completions.create(
    model="stepaudio-2.5-chat",
    messages=[
        {"role": "user", "content": "Summarize the main tradeoffs for this API workload."}
    ],
)
print(response.choices[0].message.content)