Sprachmodell (GLM-4-Voice)

GLM-4-Voice Sprachdialogmodell mit Unterstützung für Text-zu-Sprache.

API-Endpunkte

POST/audio/speech

Text-zu-Sprache

Anfrageparameter

Parameter	Typ	Erforderlich	Beschreibung
`model`	string	Erforderlich	Modellname: GLM-4-Voice
`input`	string	Erforderlich	Text, der in Sprache umgewandelt werden soll
`voice`	string	Optional	Stimmauswahl, Standard alloy

Anfrage-Beispiel

{
  "model": "GLM-4-Voice",
  "input": "你好，我是智谱AI的语音助手",
  "voice": "alloy"
}

Antwort-Beispiel

(返回音频文件流)

Code-Beispiele

Python

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://your-proxy-domain.com/v1"
)

response = client.audio.speech.create(
    model="GLM-4-Voice",
    voice="alloy",
    input="你好，我是智谱AI的语音助手"
)

# 保存音频文件
response.stream_to_file("output.mp3")

JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'your-api-key',
  baseURL: 'https://your-proxy-domain.com/v1'
});

async function generateSpeech() {
  const response = await client.audio.speech.create({
    model: 'GLM-4-Voice',
    voice: 'alloy',
    input: '你好，我是智谱AI的语音助手'
  });

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync('output.mp3', buffer);
}

generateSpeech();

cURL

curl https://your-proxy-domain.com/v1/audio/speech \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "GLM-4-Voice",
    "input": "你好，我是智谱AI的语音助手",
    "voice": "alloy"
  }' \
  --output output.mp3