Get an API key

Go to the Account Management submenu on the console and open Interface Keys to create a key.

Environment setup

Install Python dependencies

Python users can reuse the OpenAI SDK:

pip install --upgrade 'openai>=1.0'

Install cURL

Install curl with your OS package manager:

1. Debian/Ubuntu (apt):

   sudo apt-get update
   sudo apt-get install curl

2. CentOS (yum or dnf; CentOS 8+ uses dnf):

   • With yum:

   sudo yum install curl

   • With dnf (CentOS 8):

   sudo dnf install curl

3. macOS (brew; install Homebrew from brew.sh  if needed):

   brew install curl

Generate audio (TTS)

Use step-tts-2 to synthesize speech. See Generate audio for full parameters.

from pathlib import Path
from openai import OpenAI
 
client = OpenAI(api_key="STEP_API_KEY", base_url="https://api.stepfun.ai/v1")
speech_file_path = Path("step-tts.mp3")
 
response = client.audio.speech.create(
	model="step-tts-2",
	voice="cixingnansheng",
	input="StepFun intelligence, 10x possibilities for everyone.",
)
response.stream_to_file(speech_file_path)

curl --location 'https://api.stepfun.ai/v1/audio/speech' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $STEP_API_KEY" \
--data '{
	"model": "step-tts-2",
	"voice": "cixingnansheng",
	"input": "StepFun intelligence, 10x possibilities for everyone."
}' \
--output "step-tts.mp3"

Response

The response is an audio file. The SDK example writes step-tts.mp3, and the cURL example uses --output to save the audio locally.