- Third-party
- Zero data retention
OpenAI 针对实时使用优化的低延迟文本转语音模型。
| 模型信息 | |
|---|---|
| 条款和许可证 | 链接 ↗ |
| 更多信息 | 链接 ↗ |
| 零数据保留 | 是 |
| 定价 | 在 Cloudflare 仪表板中查看定价 ↗ |
用法
const response = await env.AI.run(
'openai/tts-1',
{
response_format: 'mp3',
speed: 1,
text: 'Hello! Welcome to Cloudflare AI Gateway. Let me show you what we can do.',
voice: 'alloy',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/tts-1",
"input": {
"response_format": "mp3",
"speed": 1,
"text": "Hello! Welcome to Cloudflare AI Gateway. Let me show you what we can do.",
"voice": "alloy"
}
}'{
"gatewayMetadata": {
"keySource": "Unified"
},
"result": {
"audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__tts-1/simple-speech.mp3"
},
"state": "Completed"
}示例
不同音色 — 使用 Nova 音色获得不同的语气
const response = await env.AI.run(
'openai/tts-1',
{
response_format: 'mp3',
speed: 1,
text: 'The weather today is sunny with a high of 72 degrees. Perfect for a walk in the park.',
voice: 'nova',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/tts-1",
"input": {
"response_format": "mp3",
"speed": 1,
"text": "The weather today is sunny with a high of 72 degrees. Perfect for a walk in the park.",
"voice": "nova"
}
}'{
"gatewayMetadata": {
"keySource": "Unified"
},
"result": {
"audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__tts-1/different-voice.mp3"
},
"state": "Completed"
}旁白 — 使用 Onyx 音色的较慢旁白风格
const response = await env.AI.run(
'openai/tts-1',
{
response_format: 'mp3',
speed: 0.85,
text: 'In the beginning, the universe was a singularity of infinite density. Then, in a fraction of a second, it expanded into everything we know today.',
voice: 'onyx',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/tts-1",
"input": {
"response_format": "mp3",
"speed": 0.85,
"text": "In the beginning, the universe was a singularity of infinite density. Then, in a fraction of a second, it expanded into everything we know today.",
"voice": "onyx"
}
}'{
"gatewayMetadata": {
"keySource": "Unified"
},
"result": {
"audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__tts-1/narration.mp3"
},
"state": "Completed"
}Echo 音色 — 使用 Echo 音色获得更低沉的语气
const response = await env.AI.run(
'openai/tts-1',
{
response_format: 'mp3',
speed: 1,
text: 'Welcome back to the podcast. Today we are going to talk about the future of artificial intelligence and its impact on creative work.',
voice: 'echo',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/tts-1",
"input": {
"response_format": "mp3",
"speed": 1,
"text": "Welcome back to the podcast. Today we are going to talk about the future of artificial intelligence and its impact on creative work.",
"voice": "echo"
}
}'{
"gatewayMetadata": {
"keySource": "Unified"
},
"result": {
"audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__tts-1/echo-voice.mp3"
},
"state": "Completed"
}快速播放 — 加快语速,便于快速收听
const response = await env.AI.run(
'openai/tts-1',
{
response_format: 'mp3',
speed: 1.5,
text: 'This is a fast-paced summary of the key findings from the quarterly report. Revenue is up fifteen percent, user growth exceeded expectations, and infrastructure costs remain stable.',
voice: 'shimmer',
},
)
console.log(response)curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
--header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/tts-1",
"input": {
"response_format": "mp3",
"speed": 1.5,
"text": "This is a fast-paced summary of the key findings from the quarterly report. Revenue is up fifteen percent, user growth exceeded expectations, and infrastructure costs remain stable.",
"voice": "shimmer"
}
}'{
"gatewayMetadata": {
"keySource": "Unified"
},
"result": {
"audio": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__tts-1/fast-playback.mp3"
},
"state": "Completed"
}参数
text
stringrequiredmaxLength: 4096要生成音频的文本。最大长度为 4096 个字符。voice
stringrequireddefault: alloyenum: alloy, echo, fable, onyx, nova, shimmer生成音频时使用的音色。默认为 alloy。response_format
stringrequireddefault: mp3enum: mp3, opus, wav, aac, flac音频的输出格式。支持的格式为 mp3、opus、wav、aac 和 flac。speed
numberrequireddefault: 1minimum: 0.25maximum: 4生成音频的语速。取值范围为 0.25 到 4.0,默认为 1.0。audio
string生成音频文件的 URL