返回模型列表

gpt-audio

openaiopenai/gpt-audio

API 使用指南

音频 Chat 调用

在消息内容中发送 base64 编码的 WAV/MP3 音频。模型可以用文本和音频回复。

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "modalities": ["text", "audio"],
    "audio": { "voice": "alloy", "format": "wav" },
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "What does this audio say?" },
          { "type": "input_audio", "input_audio": { "data": "<BASE64_AUDIO>", "format": "wav" } }
        ]
      }
    ]
  }'

流式音频对话

实时流式接收文本(转写)token,同时在最终消息中获取完整音频。

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "modalities": ["text", "audio"],
    "audio": { "voice": "nova", "format": "wav" },
    "stream": true,
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Tell me a story in 30 seconds." }
        ]
      }
    ]
  }'
事实档案 — 本页每条断言可在此回溯来源
来源URL采集于
发布日期OpenRouter ↗2026-05-29已核实
上下文窗口OpenRouter ↗2026-05-29待核实
最大输出长度OpenRouter ↗2026-05-29待核实
支持的模态developers.openai.com ↗2026-05-29已核实
许可——已核实
Audio quality & voice naturalnessOpenRouter ↗2026-05-29待核实
OpenAI 发布 gpt-audio——首个面向 Chat Completions 的通用音频模型OpenRouter ↗2026-05-29已核实
gpt-audio 和 gpt-4o-audio-preview 有什么区别?openrouter.ai ↗2026-05-29待核实
我能在 TheRouter API 中使用 gpt-audio 吗?api.therouter.ai ↗2026-05-29待核实
gpt-audio 支持什么音频格式输入和输出?developers.openai.com ↗2026-05-29待核实
gpt-audio 在 TheRouter 上的定价如何?api.therouter.ai ↗2026-05-29待核实
帮助与联系