Tiered speech synthesis with over 1,000 voices, 16 languages, 20 Chinese dialects, natural-language delivery direction, and inline emotion tags.
Alibaba Cloud오디오 생성출시 2026년 7월 20일Singapore독점 엔드포인트신규Tiered speech synthesis with over 1,000 voices, 16 languages, 20 Chinese dialects, natural-language delivery direction, and inline emotion tags.
Voice selection is tier aware: base voice ids work on both tiers and are automatically matched to the selected model_tier, while the six system voices are locked to one tier. Pitch also shifts the pace of the rendered audio, so pair it with speed when you want to preserve the original duration.
다른 이름 Qwen Audio TTS, Alibaba Cloud Qwen Audio 3.0 TTS, Qwen-Audio-3.0-TTS, qwen-audio-3-0-tts
qwen-audio-3-0-tts/v1/audio/speechPOST/v1/audio/speech:streamGET/v1/voicesqwen-audio-3.0-ttsalibaba/qwen-audio-3-0-ttsqwen-audio-3.0-tts-plusqwen-audio-3.0-tts-flashEmpirioLabs 카탈로그의 실시간 종량제 요금입니다. 사용한 만큼만 결제하며 월 최소 요금이 없습니다.
Qwen Audio 3.0 TTS은(는) POST /v1/audio/speech로 음성을 생성하고 재생 가능한 오디오를 반환합니다. 말할 텍스트를 input으로, 모델 ID qwen-audio-3-0-tts와 함께 보내세요. EmpirioLabs 대시보드에서 API 키를 발급받으세요.
curl https://api.empiriolabs.ai/v1/audio/speech \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-audio-3-0-tts",
"input": "Welcome to EmpirioLabs. Your build just finished."
}' \
--output speech.mp3import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/audio/speech",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={"model": "qwen-audio-3-0-tts", "input": "Welcome to EmpirioLabs."},
)
with open("speech.mp3", "wb") as f:
f.write(response.content)EmpirioLabs에서 Qwen Audio 3.0 TTS API가 지원하는 요청 파라미터입니다. 필드를 생략하면 기본값이 적용됩니다.
| 파라미터 | 유형 | 기본값 | 범위 / 값 | 설명 |
|---|---|---|---|---|
| input | string | - | 최대 20000 | Text to synthesize. Up to 20,000 characters per request. Supports inline expression tags placed directly in the text, for example [excited], [laughing], [whispers],... |
| model_tier | enum | plus | plus, flash | plus: highest audio quality and expressiveness, best for content creation, audiobooks, dubbing, and brand voice work. flash: tuned for real-time interaction with... |
| voice | enum | loongjameszhao | loongjameszhao, loongolivialin, loonglunawang, loongnorahu, l... | Voice preset. The base voices work on BOTH tiers, so changing model_tier keeps your selection. Six flagship voices are tier locked: longanlingxin and longanlufeng on... |
| voice_id | string | - | - | Free-form voice id, which overrides voice when set. Accepts any base voice from GET /v1/voices, either as the bare id (recommended, works on both tiers) or fully... |
| response_format | enum | mp3 | mp3, wav, pcm, opus | Audio container. mp3 and opus are compressed, wav is uncompressed PCM in a RIFF header, and pcm is headerless raw samples for chunked playback. |
| sample_rate | enum | 24000 | 8000, 16000, 22050, 24000, 44100, 48000 | Output sample rate in Hz. 24000 suits speech playback, and 48000 gives broadcast-quality output at a larger file size. |
| speed | number | 1 | 0.5 ~ 2 | Speaking rate multiplier. 0.5 is half speed and 2.0 is double speed. |
| pitch | number | 1 | 0.5 ~ 2 | Pitch multiplier. Values below 1.0 lower the voice and values above raise it. Pitch also shifts the pace of the rendered audio, so pair it with speed when you want... |
| volume | integer | 50 | 0 ~ 100 | Output loudness, where 50 is the reference level. |
| instruction | string | - | 최대 128 | Natural-language direction for delivery, up to 128 characters. Controls emotion, tone, character, pace, and speaking style, for example 'Speak quickly in an excited,... |
| language_hints | array | - | zh, en | Language codes that bias pronunciation for mixed-language text, for example ["zh", "en"]. Leave unset to let the model detect the language. |
| seed | integer | 0 | 0 ~ 65535 | Sampling seed. Reuse a seed with identical input and settings for a repeatable render. |
| bit_rate | integer | 32000 | 16000 ~ 64000 | Encoder bitrate in bps. Applies to the opus format only, and is ignored for mp3, wav, and pcm. |
| pronunciation | object | - | - | Pronunciation overrides keyed by the written form, for example {"重要": "zhong4 yao4"}. Use it to fix names, acronyms, and homographs. |
EmpirioLabs에서 Qwen Audio 3.0 TTS은(는) 종량제로 청구됩니다: Plus synthesis $0.20 per 10,000 characters; Flash synthesis $0.15 per 10,000 characters. 이 페이지의 실시간 요금표는 항상 API 청구 금액과 일치합니다.
Qwen Audio 3.0 TTS은(는) api.empiriolabs.ai의 POST /v1/audio/speech를 통해 제공되며 표준 Bearer 토큰 인증을 사용합니다.
네. EmpirioLabs 플레이그라운드에서 API와 동일한 파라미터로 Qwen Audio 3.0 TTS을(를) 브라우저에서 실행하므로 코드를 작성하기 전에 프롬프트를 테스트할 수 있습니다.
EmpirioLabs 계정을 만든 다음 대시보드의 API Keys에서 키를 생성하세요. 요금은 종량제 크레딧이라 실행한 요청에 대해서만 결제합니다.
