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 naturalness | OpenRouter ↗ | 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 |