Gemini 2.5 Flash TTS 文本转语音
curl --request POST \
--url https://api.highwayapi.ai/v3/gemini-2.5-flash-tts \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"contents": {
"role": "<string>",
"parts": {
"text": "<string>"
}
},
"generation_config": {
"temperature": 123,
"speech_config": {
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
},
"language_code": "<string>",
"multi_speaker_voice_config": {
"speaker_voice_configs": [
{
"speaker": "<string>",
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
}
}
]
}
}
}
}
'{
"audioContent": "<string>",
"usageMetadata": {
"totalTokenCount": 123,
"promptTokenCount": 123,
"candidatesTokenCount": 123
}
}音频
Gemini 2.5 Flash TTS 文本转语音
POST
/
v3
/
gemini-2.5-flash-tts
Gemini 2.5 Flash TTS 文本转语音
curl --request POST \
--url https://api.highwayapi.ai/v3/gemini-2.5-flash-tts \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"contents": {
"role": "<string>",
"parts": {
"text": "<string>"
}
},
"generation_config": {
"temperature": 123,
"speech_config": {
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
},
"language_code": "<string>",
"multi_speaker_voice_config": {
"speaker_voice_configs": [
{
"speaker": "<string>",
"voice_config": {
"prebuilt_voice_config": {
"voice_name": "<string>"
}
}
}
]
}
}
}
}
'{
"audioContent": "<string>",
"usageMetadata": {
"totalTokenCount": 123,
"promptTokenCount": 123,
"candidatesTokenCount": 123
}
}基于 Google Vertex AI generateContent 接口的 Gemini 2.5 Flash TTS。支持同步和流式单人/多人语音合成，通过自然语言提示词精确控制风格、口音、节奏、语调和情感表达。contents 字段最大 8000 字节，输出音频最长约 655 秒。Vertex AI 输出为 LINEAR16 PCM 格式（24kHz, 单声道），不包含 WAV 头。如需其他音频格式需客户端自行转换。
请求头
枚举值:
application/jsonBearer 身份验证格式: Bearer {{API 密钥}}。
请求体
隐藏 properties
隐藏 properties
角色，固定为 user可选值：
user隐藏 properties
隐藏 properties
要合成为语音的文本内容。Vertex AI API 将提示词和文本合并在一个字段中，格式为 ’: ‘，例如 ‘Say the following in a curious way: OK, so… tell me about this AI thing.’。总大小最多 8000 字节，超出 655 秒的音频将被截断。支持内联标记标签：[sigh]、[laughing]、[uhm]、[sarcasm]、[robotic]、[shouting]、[whispering]、[extremely fast]、[short pause]、[medium pause]、[long pause]长度限制：0 - 8000
隐藏 properties
隐藏 properties
温度参数，控制语音生成的随机性和创造性。值越高越有创意和多样性，值越低越可预测和集中。有效范围 (0.0, 2.0]，推荐值为 2.0取值范围：[0, 2]
隐藏 properties
隐藏 properties
单人语音配置。与 multi_speaker_voice_config 二选一
隐藏 properties
隐藏 properties
隐藏 properties
隐藏 properties
预置语音名称（大小写不敏感）。可选的 30 个语音（男女声均有）可选值：
Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Pulcherrima, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi语言代码（BCP-47 格式，大小写不敏感）。可选字段；不传时将根据输入文本自动识别语言。GA 语言：ar-EG, bn-BD, nl-NL, en-IN, en-US, fr-FR, de-DE, hi-IN, id-ID, it-IT, ja-JP, ko-KR, mr-IN, pl-PL, pt-BR, ro-RO, ru-RU, es-ES, ta-IN, te-IN, th-TH, tr-TR, uk-UA, vi-VN。Preview 语言包括 cmn-CN（中文普通话）等 63 种可选值：
af-ZA, am-ET, ar-001, ar-EG, az-AZ, be-BY, bg-BG, bn-BD, ca-ES, ceb-PH, cmn-CN, cmn-TW, cs-CZ, da-DK, de-DE, el-GR, en-AU, en-GB, en-IN, en-US, es-419, es-ES, es-MX, et-EE, eu-ES, fa-IR, fi-FI, fil-PH, fr-CA, fr-FR, gl-ES, gu-IN, he-IL, hi-IN, hr-HR, ht-HT, hu-HU, hy-AM, id-ID, is-IS, it-IT, ja-JP, jv-JV, ka-GE, kn-IN, ko-KR, kok-IN, la-VA, lb-LU, lo-LA, lt-LT, lv-LV, mai-IN, mg-MG, mk-MK, ml-IN, mn-MN, mr-IN, ms-MY, my-MM, nb-NO, ne-NP, nl-NL, nn-NO, or-IN, pa-IN, pl-PL, ps-AF, pt-BR, pt-PT, ro-RO, ru-RU, sd-IN, si-LK, sk-SK, sl-SI, sq-AL, sr-RS, sv-SE, sw-KE, ta-IN, te-IN, th-TH, tr-TR, uk-UA, ur-PK, vi-VN多人语音配置。与 voice_config 二选一。注意：gemini-2.5-flash-lite-preview-tts 不支持多人合成
隐藏 properties
隐藏 properties
说话人语音配置列表
隐藏 properties
隐藏 properties
说话人别名，必须仅由字母数字字符组成，不含空格。需与 contents.parts.text 中的说话人标识一致
隐藏 properties
隐藏 properties
隐藏 properties
隐藏 properties
预置语音名称（大小写不敏感）。可选的 30 个语音（男女声均有）可选值：
Achernar, Achird, Algenib, Algieba, Alnilam, Aoede, Autonoe, Callirrhoe, Charon, Despina, Enceladus, Erinome, Fenrir, Gacrux, Iapetus, Kore, Laomedeia, Leda, Orus, Pulcherrima, Puck, Rasalgethi, Sadachbia, Sadaltager, Schedar, Sulafat, Umbriel, Vindemiatrix, Zephyr, Zubenelgenubi响应信息
Base64 编码的音频内容。格式为 LINEAR16 PCM（24kHz, 单声道, 16-bit signed little-endian），不包含 WAV 头。客户端可使用 ffmpeg 转换：ffmpeg -f s16le -ar 24k -ac 1 -i input.raw output.wav
⌘I