TTS-1 vs TTS-1 HD
何时使用哪一个 — 经过整理的结论，而非基准测试表格
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。
定价
费率取自构建时的实时目录；每个模型页面均附有当前的费率卡。
它们的位置 — 以该计费单位计费的所有 7 个 文本转语音 模型的 每 1M 字符的价格（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 |
| 请求限制 | 4096 characters | 4096 characters |
| 声音 | 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 |
| 语音控制 | 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 |
规格转录自各供应商的文档；若供应商未发布某项数据，则直接省略该行，而非进行推断。 完整来源： TTS-1 · TTS-1 HD
只需一行代码即可在它们之间切换
两个 ID 都包含在下方的每个选项卡中 — 高亮显示的两行是唯一的修改。相同的端点，相同的密钥，相同的请求结构。
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？
在 每 1m 字符 方面，TTS-1 更便宜（$15 对比 $30，相差 2.0×）。其他行可能得出相反的结论——上方表格提供了完整信息，实际成本取决于你的组合使用情况。
我可以在不进行两次集成的情况下，对 TTS-1 和 TTS-1 HD 进行 A/B 测试吗？
可以。两者均通过同一个兼容 OpenAI 的端点提供服务，并使用同一把 API 密钥——切换只需更改一行模型字符串，因此你可以将一部分流量路由到各个模型并直接比较账单。
文本转语音如何计费？
按输入文本的字符数计费，每次请求的字符上限如规格表所示。无论使用哪种模型，长文本都必须在多个请求中分块。