Text-to-Speech

​

Endpoint

​

Request body

• model string required
  The ID of the model to use. Currently, only step-tts-2 is supported for the overseas region.
• input string required
  The text to generate audio for. The maximum length is 10,000 characters.
• voice string required
  The voice to use for generation. Supports both official voices and custom cloned voices.
• response_format string optional
  The audio format for the returned output. Supported formats: mp3 (default), opus, aac, flac, wav, pcm.
• speed float optional
  The speed of the generated audio. Select a value from 0.5 to 2.0. Default is 1.0.
• volume float optional
  The volume of the generated audio. The valid range is 0.1 to 2.0, with a default value of 1.0. 0.1 reduces the volume to 10%, while 2.0 increases it to 200%.
• voice_label object optional
  Voice tags. Required when using a custom voice. Only one of language, emotion, or style can be set at a time.
  • language string optional
    Language. Supports Cantonese, Sichuanese, and Japanese. If not specified, the system automatically determines whether the input text is English or Chinese.
  • emotion string optional
    Emotion. Supports up to 11 options such as Happy, Angry, and more. Supported emotion and style labels can be found in the Voice Label Reference.
  • style string optional
    Supports up to 17 speaking rates or delivery styles. Supported emotion and style labels can be found in the Voice Label Reference
• sample_rate integer optional
  The sampling rate. Supports 8000, 16000, 22050, 24000, 48000. Default is 24000. Higher rates improve quality but increase file size.
• pronunciation_map object array optional
  Defines a pronunciation rule to annotate or override the reading of specific characters or symbols. In Chinese text, tones are represented by numbers 1–5.
  • tone string required
    Specific pronunciation mapping rules, separated by /. Example: ["omg/oh my god"].
• stream_format string optional
  Streaming return mode. By default, audio is returned directly. Supported values: sse, audio. Default is audio. When sse is specified, audio is returned via Server-Sent Events (SSE).

​

Response

​

Examples

from pathlib import Path
from openai import OpenAI

speech_file_path = Path("step-tts.mp3")

client = OpenAI(
  api_key="STEP_API_KEY",
  base_url="https://api.stepfun.ai/v1",
)

response = client.audio.speech.create(
  model="step-tts-2",
  voice="lively-girl",
  input="StepFun is building the next generation of AGI.",
  extra_body={
      "volume": 1.0,  # volume is in extra_body
      "voice_label": {
          "language": "Cantonese",  # choose one of language / emotion / style
      },
      "pronunciation_map": {
          "tone": [
              "LOL/laugh out loudly",
          ],
      },
  },
)

response.stream_to_file(speech_file_path)

import OpenAI from "openai";
import fs from "fs";
import path from "path";

const STEP_API_KEY =
"STEP_API_KEY";
const STEP_API_MODEL = "step-tts-2";

const openai = new OpenAI({
apiKey: STEP_API_KEY,
baseURL: "https://api.stepfun.ai/v1",
});

async function main() {
const speechFile = path.resolve("./speech.mp3");
const mp3 = await openai.audio.speech.create({
  model: STEP_API_MODEL,
  voice: "lively-girl",
  input: "StepFun is building the next generation of AGI.",
  extra_body:{
    "volume":2.0, // volume is in extra_body
    "voice_label": {
      "language": "Cantonese"  // Optional: choose one of language/emotion/style
    },
    "pronunciation_map":{
      "tone":[
          "LOL/laugh out loudly"
      ]
    }
  }
});
console.log(speechFile);
const buffer = Buffer.from(await mp3.arrayBuffer());
await fs.promises.writeFile(speechFile, buffer);
}

main();

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",
    "input":"StepFun is building the next generation of AGI.",
    "voice":"lively-girl"
}'\
--output "step.mp3"