TTS-1 vs TTS-1 HD
什么时候选哪个
同样的 4096 字符上限、同样支持流式、同样的音色集合，也同样都没有音色控制；tts-1-hd 每百万字符 $30 对 $15，正好 2 倍，换来更高质量的合成。已公布的规格里没有别的差异。做草稿和走量选 tts-1，音频要交付给用户时选 tts-1-hd。
价格
价格取自构建时的实时目录，最新价格见各模型页面。
两个模型所处的位置：全部 7 个按同一单位计费的文字转语音模型的每 1M 字符价格分布（对数刻度）
能力
规格
| TTS-1 | TTS-1 HD | |
|---|---|---|
| 输入模态 | 文本 | 文本 |
| 输出模态 | 音频 | 音频 |
| 发布日期 | 2023-11-06 | 2023-11-06 |
| 请求限制 | 4096 characters | 4096 characters |
| 音色 | alloy, ash, coral, echo, fable, onyx, nova, sage and shimmer, a smaller set than the full 13-voice TTS list, and voices are currently optimized for English. | alloy, ash, coral, echo, fable, onyx, nova, sage and shimmer, a smaller set than the full 13-voice TTS list, and voices are currently optimized for English. |
| 语言 | Generally follows the Whisper model’s language support: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese and Welsh, despite voices being optimized for English | Generally follows the Whisper model’s language support: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese and Welsh, despite voices being optimized for English |
| 声音控制 | none | none |
| 限制 | Speech generation endpoint (v1/audio/speech) only, with Chat Completions, Responses, Realtime, Batch and Fine-tuning all listed as not supported input text is capped at 4096 characters output mp3 (default), opus, aac, flac, wav or pcm (raw 24 kHz 16-bit signed little-endian samples) realtime playback via chunked transfer encoding | Speech generation endpoint (v1/audio/speech) only, with Chat Completions, Responses, Realtime, Batch and Fine-tuning all listed as not supported input text is capped at 4096 characters output mp3 (default), opus, aac, flac, wav or pcm (raw 24 kHz 16-bit signed little-endian samples) realtime playback via chunked transfer encoding |
规格照录自各供应商的文档；供应商没有公布的项目，对应的行直接省略，不做推断。 完整来源： TTS-1 · TTS-1 HD
改一行代码就能在两个模型之间切换
下方每个标签页里都有两个模型 ID，高亮的那两行是唯一要改的地方。端点不变，API key 不变，请求结构也不变。
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.audio.transcriptions.create(
model="tts-1",
# model="tts-1-hd", # 取消注释此行，注释上一行
file=open("meeting.mp3", "rb"),
language="en",
)
print(resp.text)import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.audio.transcriptions.create({
model: "tts-1",
// model: "tts-1-hd", // 取消注释此行，注释上一行
file: fs.createReadStream("meeting.mp3"),
});
console.log(resp.text);curl https://synthorai.io/v1/audio/transcriptions \
-H "Authorization: Bearer sk-syn-..." \
-F model="tts-1" \
# -F model="tts-1-hd" \ # 取消注释此行，注释上一行
-F file=@meeting.mp3package main
import (
"context"
"fmt"
"os"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
f, _ := os.Open("meeting.mp3")
resp, _ := client.Audio.Transcriptions.New(context.TODO(), openai.AudioTranscriptionNewParams{
Model: "tts-1",
// Model: "tts-1-hd", // 取消注释此行，注释上一行
File: f,
})
fmt.Println(resp.Text)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.audio.transcriptions.*;
import java.nio.file.Paths;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
Transcription resp = client.audio().transcriptions().create(
TranscriptionCreateParams.builder()
.model("tts-1")
// .model("tts-1-hd") // 取消注释此行，注释上一行
.file(Paths.get("meeting.mp3"))
.build()).asTranscription();
System.out.println(resp.text());常见问题
TTS-1 和 TTS-1 HD 哪个更便宜？
按「每 1M 字符」算，TTS-1 更便宜（$15 对 $30，相差 2.0×）。其他计费项的结论可能相反，完整价格见上方表格，实际成本取决于你的用量构成。
不用分别集成两次，就能对 TTS-1 和 TTS-1 HD 做 A/B 测试吗？
可以。两个模型走同一个 OpenAI 兼容端点，用同一个 API key，切换时只要改一行里的模型名，所以可以给两个模型各分一部分流量，直接对比账单。
文字转语音如何计费？
按输入文本的字符数计费，单次请求的字符上限见规格表。不管用哪个模型，长文本都得拆成多个请求。