Fish Audio S2 Pro Text to Speech

POST /v3/fish-audio-s2-pro-text-to-speech

Fish Audio S2 Pro Text to Speech

cURL

curl --request POST \
  --url https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "text": "<string>",
  "top_p": 123,
  "format": "<string>",
  "latency": "<string>",
  "prosody": {
    "speed": 123,
    "volume": 123,
    "normalize_loudness": true
  },
  "normalize": true,
  "references": [
    {
      "text": "<string>",
      "audio": "<string>"
    }
  ],
  "mp3_bitrate": 123,
  "sample_rate": 123,
  "temperature": 123,
  "chunk_length": 123,
  "opus_bitrate": 123,
  "reference_id": "<string>",
  "max_new_tokens": 123,
  "min_chunk_length": 123,
  "repetition_penalty": 123,
  "early_stop_threshold": 123,
  "condition_on_previous_chunks": true
}
'

import requests

url = "https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech"

payload = {
    "text": "<string>",
    "top_p": 123,
    "format": "<string>",
    "latency": "<string>",
    "prosody": {
        "speed": 123,
        "volume": 123,
        "normalize_loudness": True
    },
    "normalize": True,
    "references": [
        {
            "text": "<string>",
            "audio": "<string>"
        }
    ],
    "mp3_bitrate": 123,
    "sample_rate": 123,
    "temperature": 123,
    "chunk_length": 123,
    "opus_bitrate": 123,
    "reference_id": "<string>",
    "max_new_tokens": 123,
    "min_chunk_length": 123,
    "repetition_penalty": 123,
    "early_stop_threshold": 123,
    "condition_on_previous_chunks": True
}
headers = {
    "Content-Type": "<content-type>",
    "Authorization": "<authorization>"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
  body: JSON.stringify({
    text: '<string>',
    top_p: 123,
    format: '<string>',
    latency: '<string>',
    prosody: {speed: 123, volume: 123, normalize_loudness: true},
    normalize: true,
    references: [{text: '<string>', audio: '<string>'}],
    mp3_bitrate: 123,
    sample_rate: 123,
    temperature: 123,
    chunk_length: 123,
    opus_bitrate: 123,
    reference_id: '<string>',
    max_new_tokens: 123,
    min_chunk_length: 123,
    repetition_penalty: 123,
    early_stop_threshold: 123,
    condition_on_previous_chunks: true
  })
};

fetch('https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'text' => '<string>',
    'top_p' => 123,
    'format' => '<string>',
    'latency' => '<string>',
    'prosody' => [
        'speed' => 123,
        'volume' => 123,
        'normalize_loudness' => true
    ],
    'normalize' => true,
    'references' => [
        [
                'text' => '<string>',
                'audio' => '<string>'
        ]
    ],
    'mp3_bitrate' => 123,
    'sample_rate' => 123,
    'temperature' => 123,
    'chunk_length' => 123,
    'opus_bitrate' => 123,
    'reference_id' => '<string>',
    'max_new_tokens' => 123,
    'min_chunk_length' => 123,
    'repetition_penalty' => 123,
    'early_stop_threshold' => 123,
    'condition_on_previous_chunks' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "Content-Type: <content-type>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech"

	payload := strings.NewReader("{\n  \"text\": \"<string>\",\n  \"top_p\": 123,\n  \"format\": \"<string>\",\n  \"latency\": \"<string>\",\n  \"prosody\": {\n    \"speed\": 123,\n    \"volume\": 123,\n    \"normalize_loudness\": true\n  },\n  \"normalize\": true,\n  \"references\": [\n    {\n      \"text\": \"<string>\",\n      \"audio\": \"<string>\"\n    }\n  ],\n  \"mp3_bitrate\": 123,\n  \"sample_rate\": 123,\n  \"temperature\": 123,\n  \"chunk_length\": 123,\n  \"opus_bitrate\": 123,\n  \"reference_id\": \"<string>\",\n  \"max_new_tokens\": 123,\n  \"min_chunk_length\": 123,\n  \"repetition_penalty\": 123,\n  \"early_stop_threshold\": 123,\n  \"condition_on_previous_chunks\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "<content-type>")
	req.Header.Add("Authorization", "<authorization>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech")
  .header("Content-Type", "<content-type>")
  .header("Authorization", "<authorization>")
  .body("{\n  \"text\": \"<string>\",\n  \"top_p\": 123,\n  \"format\": \"<string>\",\n  \"latency\": \"<string>\",\n  \"prosody\": {\n    \"speed\": 123,\n    \"volume\": 123,\n    \"normalize_loudness\": true\n  },\n  \"normalize\": true,\n  \"references\": [\n    {\n      \"text\": \"<string>\",\n      \"audio\": \"<string>\"\n    }\n  ],\n  \"mp3_bitrate\": 123,\n  \"sample_rate\": 123,\n  \"temperature\": 123,\n  \"chunk_length\": 123,\n  \"opus_bitrate\": 123,\n  \"reference_id\": \"<string>\",\n  \"max_new_tokens\": 123,\n  \"min_chunk_length\": 123,\n  \"repetition_penalty\": 123,\n  \"early_stop_threshold\": 123,\n  \"condition_on_previous_chunks\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.highwayapi.ai/v3/fish-audio-s2-pro-text-to-speech")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n  \"text\": \"<string>\",\n  \"top_p\": 123,\n  \"format\": \"<string>\",\n  \"latency\": \"<string>\",\n  \"prosody\": {\n    \"speed\": 123,\n    \"volume\": 123,\n    \"normalize_loudness\": true\n  },\n  \"normalize\": true,\n  \"references\": [\n    {\n      \"text\": \"<string>\",\n      \"audio\": \"<string>\"\n    }\n  ],\n  \"mp3_bitrate\": 123,\n  \"sample_rate\": 123,\n  \"temperature\": 123,\n  \"chunk_length\": 123,\n  \"opus_bitrate\": 123,\n  \"reference_id\": \"<string>\",\n  \"max_new_tokens\": 123,\n  \"min_chunk_length\": 123,\n  \"repetition_penalty\": 123,\n  \"early_stop_threshold\": 123,\n  \"condition_on_previous_chunks\": true\n}"

response = http.request(request)
puts response.read_body

Fish Audio S2 Pro 文本转语音模型，将文本转换为自然语音，支持参考音色、采样控制、分段、音频格式和韵律控制。

​

请求头

Content-Type · string · 必填

枚举值: application/json

Authorization · string · 必填

Bearer 身份验证格式: Bearer {{API 密钥}}。

​

请求体

text · string · 必填

需要转换为语音的文本。S2-Pro 多说话人文本可使用 <|speaker:0|>你好<|speaker:1|>你好呀 标签。

top_p · number

核采样多样性控制。

取值范围：[0, 1]

format · string · 默认值: "mp3"

输出音频格式。

可选值：wav, pcm, mp3, opus

latency · string · 默认值: "normal"

延迟档位。

可选值：low, normal, balanced

prosody · object

韵律控制。

隐藏 properties

speed · number · 默认值: 1

语速倍率。

volume · number · 默认值: 0

音量调整。

normalize_loudness · boolean · 默认值: true

是否规范化输出响度。

normalize · boolean · 默认值: true

对中英文文本进行规范化。

references · object[]

用于零样本声音克隆的参考音频样本。

隐藏 properties

text · string

参考音频对应文本。

audio · string

参考音频，按供应商支持传入 base64 或 URL。

mp3_bitrate · integer · 默认值: 128

MP3 比特率，单位 kbps。

可选值：64, 128, 192

sample_rate · integer

输出采样率 Hz。为空时使用格式默认值，opus 为 48000 Hz，其他通常为 44100 Hz。

temperature · number

表现力控制。

取值范围：[0, 1]

chunk_length · integer · 默认值: 300

文本分段大小。

取值范围：[100, 300]

opus_bitrate · integer

Opus 比特率，单位 bps，-1000 表示自动。

可选值：-1000, 24000, 32000, 48000, 64000

reference_id · string

音色模型 ID；多说话人场景可传入与 speaker 索引匹配的数组。

max_new_tokens · integer · 默认值: 1024

每个分段的最大音频 token 数。

min_chunk_length · integer · 默认值: 50

分段前的最小字符数。

取值范围：[0, 100]

repetition_penalty · number

降低音频模式重复的惩罚系数。

early_stop_threshold · number · 默认值: 1

提前停止阈值。

取值范围：[0, 1]

condition_on_previous_chunks · boolean · 默认值: true

使用前序音频分段作为上下文。

​

响应信息

生成的音频。

格式: binary