Real-time long-text-to-speech SDK API and error code information-Intelligent Speech Interaction(ISI)-阿里云帮助中心

The long-text-to-speech feature converts extra-long text, such as text with thousands of words, into binary speech data.

Note

The Speech Synthesis product page provides samples for most voices. If the voice you want is not available on the product page, you can call the API to listen to a sample. For more information about the API, see Java SDK and C++ SDK.

Billing and concurrency limits

Real-time long-text-to-speech is available only in the commercial version and does not support a free trial. For more information, see Trial and commercial versions. To use this feature, you must activate the commercial version. For more information, see Upgrade from the trial version to the commercial version.
For more information about billing methods, see Billing methods.
For more information about concurrency limits, see Concurrency and QPS limits.

Features

Supports PCM, WAV, and MP3 encoding formats for output data.
Supports adjustments for speech rate, pitch, and volume.
Supports male and female voices.
Long-text-to-speech has unique advantages over standard speech synthesis:
- Supports longer text input. You can synthesize up to 10,000 characters in a single request. Each Chinese character, English letter, punctuation mark, or space counts as one character.
- Exclusive voices: Provides high-quality, exclusive voices tailored for specific scenarios, such as reading novels, news, and video dubbing.
Supports multi-emotional voices. For more information, see the <emotion> tag in Markup language. Tags do not count as characters.

Important

To use the long-text-to-speech feature, update your SDK to the latest version.

Voice list

Note

To listen to more voice samples, go to the Speech Synthesis product page. The product page provides samples for most voices. If the voice you want is not available on the product page, you can call the API to listen to a sample. For more information about the API, see Java SDK and C++ SDK.

Name	voice parameter value	Type	Scenarios	Supported languages	Supported sample rates (Hz)	Supports word/sentence-level timestamps	Supports r-sound	Voice quality
Abin	abin	Cantonese-accented Mandarin	Conversational digital human	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	No	No	Standard Edition
Zhixiaobai	zhixiaobai	Mandarin female voice	Conversational digital human	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	No	Yes	Standard Edition
Zhixiaoxia	zhixiaoxia	Mandarin female voice	Conversational digital human	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	No	Yes	Standard Edition
Zhixiaomei	zhixiaomei	Mandarin female voice	Livestreaming digital human	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	Yes	Standard Edition
Zhigui	zhigui	Mandarin female voice	Livestreaming digital human	Supports Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Standard Edition
Zhishuo	zhishuo	Mandarin male voice	Customer service digital human	Supports Chinese and Chinese-English mixed scenarios	8 K/16 K	Yes	Yes	Standard Edition
Aixia	aixia	Mandarin female voice	Customer service digital human	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Standard Edition
Cally	cally	American English female voice	Spoken English conversational digital human	Supports English-only scenarios	8K or 16K	Yes	Yes	Standard Edition
Zhifeng_Multi-emotional	zhifeng_emo	Multi-emotional male voice	General	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	Yes	Standard Edition
Zhibing_Multi-emotional	zhibing_emo	Multi-emotional male voice	General	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	Yes	Yes	Standard Edition
Zhimiao_Multi-emotional	zhimiao_emo	Multi-emotional female voice	Chinese-English scenarios	Chinese and English scenarios	8K/16K	Yes	Yes	Standard Edition
Zhimi_Multi-emotional	zhimi_emo	Multi-emotional female voice	General	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Standard Edition
Zhiyan_Multi-emotional	zhiyan_emo	Multi-emotional female voice	General	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Standard Edition
Zhibei_Multi-emotional	zhibei_emo	Multi-emotional child voice	General	Chinese and Chinese-English mixed scenarios	8 K/16 K	Yes	No	Standard Edition
Zhitian_Multi-emotional	zhitian_emo	Multi-emotional female voice	General	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Standard Edition
Xiaoyun	xiaoyun	Standard female voice	General	Chinese and Chinese-English mixed scenarios	8K/16K	No	No	Lite Edition
Xiaogang	xiaogang	Standard male voice	General	Chinese and Chinese-English mixed scenarios	8K or 16K	No	No	Lite Edition
Ruoxi	ruoxi	Gentle female voice	General	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Siqi	siqi	Gentle female voice	General	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
Sijia	sijia	Standard female voice	General	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Sicheng	sicheng	Standard male voice	General	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
Aiqi	aiqi	Gentle female voice	General	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Standard Edition
Aijia	aijia	Standard female voice	General	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Standard Edition
Aicheng	aicheng	Standard male voice	General	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Standard Edition
Aida	aida	Standard male voice	General	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Standard Edition
Ninger	ninger	Standard female voice	General	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Ruilin	ruilin	Standard female voice	General	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Siyue	siyue	Gentle female voice	Customer service	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
Aiya	aiya	Stern female voice	Customer service	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Standard Edition
Aimei	aimei	Sweet female voice	Customer service	Chinese and Chinese-English mixed scenarios	8 K/16 K	Yes	No	Standard Edition
Aiyu	aiyu	Natural female voice	Customer service	Chinese and Chinese-English mixed scenarios	8 K or 16 K	Yes	No	Standard Edition
Aiyue	aiyue	Gentle female voice	Customer service	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Standard Edition
Aijing	aijing	Stern female voice	Customer service	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Standard Edition
Xiaomei	xiaomei	Sweet female voice	Customer service	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Aina	aina	Zhejiang-accented Mandarin female voice	Customer service	Chinese-only scenarios	8K or 16K	Yes	No	Standard Edition
Yina	yina	Zhejiang-accented Mandarin female voice	Customer service	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Sijing	sijing	Stern female voice	Customer service	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
Sitong	sitong	Child voice	Child voice scenarios	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Xiaobei	xiaobei	Lolita female voice	Child voice scenarios	Chinese-only scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
Aitong	aitong	Child voice	Child voice scenarios	Chinese-only scenarios	8K or 16K	Yes	No	Standard Edition
Aiwei	aiwei	Lolita female voice	Child voice scenarios	Chinese-only scenarios	8K/16K	Yes	No	Standard Edition
Aibao	aibao	Lolita female voice	Child voice scenarios	Chinese-only scenarios	8K/16K	Yes	No	Standard Edition
Harry	harry	British English male voice	English scenarios	English scenarios	8K or 16K	No	No	Standard Edition
Abby	abby	American English female voice	English scenarios	English scenarios	8K or 16K	Yes	No	Standard Edition
Andy	andy	American English male voice	English scenarios	English scenarios	8K or 16K	Yes	No	Standard Edition
Eric	eric	British English male voice	English scenarios	English scenarios	8K or 16K	Yes	No	Standard Edition
Emily	emily	British English female voice	English scenarios	English scenarios	8K or 16K	Yes	No	Standard Edition
Luna	luna	British English female voice	English scenarios	English scenarios	8K/16K	Yes	No	Standard Edition
Luca	luca	British English male voice	English scenarios	English scenarios	8K/16K	Yes	No	Standard Edition
Wendy	wendy	British English female voice	English scenarios	English scenarios	8 K, 16 K, or 24 K	No	No	Standard Edition
William	william	British English male voice	English scenarios	English scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Olivia	olivia	British English female voice	English scenarios	English scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Shanshan	shanshan	Cantonese female voice	Dialect scenarios	Standard Cantonese (Simplified Chinese) and Cantonese-English mixed scenarios	8 kHz/16 kHz/24 kHz	No	No	Standard Edition
Aiyuan	aiyuan	Trusted Advisor	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Premium Edition
Aiying	aiying	Cute child voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz	Yes	Yes	Premium Edition
Aixiang	aixiang	Magnetic male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8 K or 16 K	Yes	Yes	Premium Edition
Aimo	aimo	Emotional male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Premium Edition
Aiye	aiye	Young male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Premium Edition
Aiting	aiting	Radio female voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Premium Edition
Aifan	aifan	Emotional female voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8 K/16 K	Yes	Yes	Premium Edition
Lydia	lydia	Bilingual English-Chinese female voice	English scenarios	English and English-Chinese mixed scenarios	8 kHz/16 kHz	Yes	No	Standard Edition
Xiaoyue	chuangirl	Sichuan dialect female voice	Dialect scenarios	Chinese and Chinese-English mixed scenarios	8 K/16 K	No	No	Standard Edition
Aishuo	aishuo	Natural male voice	Customer service	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Standard Edition
Qingqing	qingqing	Taiwanese Mandarin female voice	Dialect scenarios	Chinese-only scenarios	8 kHz/16 kHz	No	No	Standard Edition
Cuijie	cuijie	Northeastern dialect female voice	Dialect scenarios	Chinese-only scenarios	8 K/16 K	Yes	Yes	Standard Edition
Xiaoze	xiaoze	Hunanese heavy-accent male voice	Dialect scenarios	Chinese-only scenarios	8K or 16K	No	No	Standard Edition
Ainan	ainan	Advertisement male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Premium Edition
Aihao	aihao	News male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Premium Edition
Aiming	aiming	Humorous male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Premium Edition
Aixiao	aixiao	News female voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Premium Edition
Aichu	aichu	Food documentary male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Premium Edition
Aiqian	aiqian	News female voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8 K/16 K	Yes	Yes	Premium Edition
Tomoka	tomoka	Japanese female voice	Multilingual scenarios	Japanese-only scenarios	8K / 16K	Yes	No	Standard Edition
Tomoya	tomoya	Japanese male voice	Multilingual scenarios	Japanese-only scenarios	8K / 16K	Yes	No	Standard Edition
Annie	annie	American English female voice	English scenarios	English-only scenarios	8K or 16K	Yes	No	Standard Edition
Aishu	aishu	News male voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Premium Edition
Airu	airu	News female voice	Literary scenarios	Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Premium Edition
Jiajia	jiajia	Cantonese female voice	Dialect scenarios	Standard Cantonese (Simplified Chinese) and Cantonese-English mixed scenarios	8 K/16 K	Yes	No	Standard Edition
Indah	indah	Indonesian female voice	Multilingual scenarios	Indonesian-only scenarios	8K or 16K	No	No	Standard Edition
Peach	taozi	Cantonese female voice	Dialect scenarios	Supports Standard Cantonese (Simplified Chinese) and Cantonese-English mixed scenarios	8K/16K	Yes	No	Standard Edition
Sales associate	guijie	Friendly female voice	General	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz	Yes	Yes	Standard Edition
Stella	stella	Intellectual female voice	General	Supports Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Standard Edition
Stanley	stanley	Calm male voice	General	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Standard Edition
Kenny	kenny	Calm male voice	General	Supports Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Standard Edition
Rosa	rosa	Natural female voice	General	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Standard Edition
Farah	farah	Malay female voice	Multilingual scenarios	Supports Malay-only scenarios	8K/16K	No	No	Standard Edition
Mashu	mashu	Children's drama male voice	General	General	8K/16K	Yes	No	Standard Edition
Zhiqi	zhiqi	Gentle female voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhichu	zhichu	Food documentary male voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	Yes	Premium Edition
Xiaoxian	xiaoxian	Friendly female voice	Livestreaming scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz	Yes	Yes	Standard Edition
Yuer	yuer	Children's drama female voice	General	Supports Chinese-only scenarios	8K or 16K	Yes	No	Standard Edition
Maoxiaomei	maoxiaomei	Energetic female voice	Livestreaming scenarios	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Standard Edition
Zhixiang	zhixiang	Magnetic male voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhijia	zhijia	Standard female voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhinan	zhinan	Advertisement male voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhiqian	zhiqian	News female voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhiru	zhiru	News female voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhide	zhide	News male voice	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Zhifei	zhifei	Passionate commentary	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	No	Premium Edition
Aifei	aifei	Passionate commentary	Livestreaming scenarios	Supports Chinese and Chinese-English mixed scenarios	8 K or 16 K	Yes	Yes	Standard Edition
Subgroup	yaqun	Store broadcast	Livestreaming scenarios	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Standard Edition
Qiaowei	qiaowei	Store broadcast	Livestreaming scenarios	Supports Chinese and Chinese-English mixed scenarios	8K/16K	Yes	Yes	Standard Edition
Dahu	dahu	Northeastern dialect male voice	Dialect scenarios	Supports Chinese and Chinese-English mixed scenarios	8K or 16K	Yes	Yes	Standard Edition
ava	ava	American English female voice	English scenarios	Supports English-only scenarios	8 K/16 K	Yes	No	Standard Edition
Zhilun	zhilun	Suspense commentary	Ultra-high definition scenarios	Supports Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Premium Edition
Ailun	ailun	Suspense commentary	Livestreaming scenarios	Supports Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz	Yes	Yes	Standard Edition
Jielidou	jielidou	Healing a Child's Voice	Child voice scenarios	Supports Chinese-only scenarios	8K or 16K	Yes	Yes	Standard Edition
Zhiwei	zhiwei	Sweet Female Voice	Ultra-high definition scenarios	Supports Chinese-only scenarios	8 kHz/16 kHz/24 kHz/48 kHz	Yes	No	Premium Edition
Laotie	laotie	Northeastern buddy	Livestreaming scenarios	Supports Chinese-only scenarios	8K/16K	Yes	Yes	Standard Edition
Younger sister	laomei	Female Hawker	Livestreaming scenarios	Supports Chinese-only scenarios	8K or 16K	Yes	Yes	Standard Edition
Aikan	aikan	Tianjin dialect male voice	Dialect scenarios	Supports Chinese-only scenarios	8K/16K	Yes	Yes	Standard Edition
Tala	tala	Filipino female voice	Multilingual scenarios	Supports Filipino-only scenarios	8K or 16K	No	No	Standard Edition
Zhitian	zhitian	Sweet female voice	General	Supports Chinese and Chinese-English mixed scenarios	8K/16K	Yes	No	Premium Edition
Zhiqing	zhiqing	Taiwan (China) dialect female voice	Dialect scenarios	Supports Chinese-only scenarios	8K or 16K	Yes	No	Premium Edition
Tien	tien	Vietnamese female voice	Multilingual scenarios	Supports Vietnamese-only scenarios	8K/16K	No	No	Standard Edition
Becca	becca	American English customer service female voice	American English	Supports English-only scenarios	8K or 16K	No	No	Standard Edition
Kyong	Kyong	Korean female voice	Korean scenarios	Korean	8 kHz/16 kHz	No	No	Standard Edition
masha	masha	Russian female voice	Russian scenarios	Russian	8K/16K	No	No	Standard Edition
camila	camila	Spanish female voice	Spanish scenarios	Spanish	8 kHz/16 kHz	No	No	Standard Edition
perla	perla	Italian female voice	Italian scenarios	Italian	8 kHz/16 kHz	No	No	Standard Edition
Zhimao	zhimao	Mandarin female voice	Livestreaming	Chinese	8 kHz/16 kHz	Yes	No	Standard Edition
Zhiyuan	zhiyuan	Mandarin female voice	General	Chinese	8 kHz/16 kHz	Yes	No	Standard Edition
Zhiya	zhiya	Mandarin female voice	Customer service	Chinese	8 kHz/16 kHz	Yes	No	Standard Edition
Zhiyue	zhiyue	Mandarin female voice	General	Chinese	8 kHz/16 kHz	Yes	No	Standard Edition
Zhida	zhida	Mandarin male voice	General	Chinese and Chinese-English mixed scenarios	8 kHz/16 kHz	Yes	No	Standard Edition
Zhi Sha	zhistella	Mandarin female voice	General	Chinese	8 kHz/16 kHz	Yes	No	Standard Edition
Kelly	kelly	Hong Kong Cantonese female voice	Dialect scenarios	Hong Kong Cantonese	8 kHz/16 kHz	Yes	No	Standard Edition
clara	clara	French female voice	General	French	8 kHz/16 kHz	No	No	Standard Edition
hanna	hanna	German female voice	General	German	8 kHz/16 kHz	No	No	Standard Edition
waan	waan	Thai female voice	General	Thai	8 kHz/16 kHz	No	No	Standard Edition
betty	betty	American English female voice	General	American English	8 kHz/16 kHz	Yes	No	Standard Edition
beth	beth	American English female voice	General	American English	8 kHz/16 kHz	Yes	No	Standard Edition
cindy	cindy	American English female voice	General	American English	8 kHz/16 kHz	Yes	No	Standard Edition
donna	donna	American English female voice	General	American English	8 kHz/16 kHz	Yes	No	Standard Edition
eva	eva	American English female voice	General	American English	8 kHz/16 kHz	Yes	No	Standard Edition
brian	brian	American English male voice	General	American English	8 kHz/16 kHz	Yes	No	Standard Edition
david	david	American English male voice	General	American English	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
abby_ecmix	abby_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
annie_ecmix	annie_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
andy_ecmix	andy_ecmix	American English male voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
ava_ecmix	ava_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
betty_ecmix	betty_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
beth_ecmix	beth_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
brian_ecmix	brian_ecmix	American English male voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
cindy_ecmix	cindy_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
cally_ecmix	cally_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
donna_ecmix	donna_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
david_ecmix	david_ecmix	American English male voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition
eva_ecmix	eva_ecmix	American English female voice	General	English and English-Chinese mixed scenarios	8 kHz/16 kHz/24 kHz	Yes	No	Standard Edition

Support for multi-emotional voices

Only multi-emotional voice models support emotion selection. The supported emotions are listed in the following table. The supported emotion categories vary by voice. The main categories include neutral, happy, angry, sad, fear, hate, surprise, arousal, serious, disgust, jealousy, embarrassed, frustrated, affectionate, gentle, newscast, customer service, and living.

Voice name	voice parameter value	Emotion category
Zhifeng_Multi-emotional	zhifeng_emo	angry, fear, happy, neutral, sad, surprise
Zhibing_Multi-emotional	zhibing_emo	angry, fear, happy, neutral, sad, surprise
Zhimiao_Multi-emotional	zhimiao_emo	serious, sad, disgust, jealousy, embarrassed, happy, fear, surprise, neutral, frustrated, affectionate, gentle, angry, newscast, customer-service, story, living
Zhimi_Multi-emotional	zhimi_emo	angry, fear, happy, hate, neutral, sad, surprise
Zhiyan_Multi-emotional	zhiyan_emo	neutral, happy, angry, sad, fear, hate, surprise, arousal
Zhibei_Multi-emotional	zhibei_emo	neutral, happy, angry, sad, fear, hate, surprise
Zhitian_Multi-emotional	zhitian_emo	neutral, happy, angry, sad, fear, hate, surprise

Call instructions

The input text must be UTF-8 encoded.
Long text-to-speech and standard speech synthesis share many similarities.

Intelligent access to the nearest region

Speech Synthesis supports intelligent access to the nearest region using the domain name nls-gateway.aliyuncs.com.

Connect to the nearest region for optimal performance. The system automatically resolves requests to the server in the nearest region based on the client's geographical location. For example, a request from the China (Beijing) region is automatically routed to a server in the China (Beijing) region. This provides the same result as specifying the nls-gateway-cn-beijing.aliyuncs.com domain name.

Service endpoints

Access type	Description	URL
Public access (defaults to the China (Shanghai) region)	All servers can use the public access URL. The SDK is configured with the public access URL by default.	China (Shanghai): `wss://nls-gateway-cn-shanghai.aliyuncs.com/ws/v1` China (Beijing): `wss://nls-gateway-cn-beijing.aliyuncs.com/ws/v1` China (Shenzhen): `wss://nls-gateway-cn-shenzhen.aliyuncs.com/ws/v1`
ECS private network access	If you use an Alibaba Cloud ECS instance in the China (Shanghai), China (Beijing), or China (Shenzhen) region, you can use the private network access URL. ECS instances in the classic network cannot access AnyTunnel and therefore cannot access the Voice Service over the private network. To use AnyTunnel, create a Virtual Private Cloud (VPC) and access the service from within the VPC. Note Private network access does not incur data transfer costs for your ECS instance. For more information about ECS network types, see Network types.	China (Shanghai): `ws://nls-gateway-cn-shanghai-internal.aliyuncs.com:80/ws/v1` China (Beijing): `ws://nls-gateway-cn-beijing-internal.aliyuncs.com:80/ws/v1` China (Shenzhen): `ws://nls-gateway-cn-shenzhen-internal.aliyuncs.com:80/ws/v1`

Interaction flow

Note

The preceding figure does not show the interaction flow for the RESTful API. For the RESTful API interaction flowchart, see RESTful API.
In addition to the audio stream, the server response header includes the `task_id` parameter. This parameter is the unique ID of the request.
To play the audio stream that is returned by the server in real time, use an audio player that supports stream playback, such as ffmpeg, PyAudio (Python), AudioFormat (Java), or MediaSource (JavaScript).

Authentication
The client uses a token for authentication when establishing a WebSocket connection with the server. For more information about obtaining a token, see Obtain a token.

Start synthesis

The client sends a speech synthesis request and configures parameters in the request message. You can set each parameter using the corresponding `set` method of the `SpeechSynthesizer` object in the SDK. The parameters are described in the following table.

Parameter	Type	Required	Description
appkey	String	Yes	The AppKey of the project that you created in the console.
text	String	Yes	The text to synthesize. The text must be `UTF-8` encoded. Add a space between English words. Note To use a multi-emotional voice, add the `ssml-emotion` tag to the text. For more information, see <emotion>. Only voices that support multiple emotions can use the <emotion> tag. Otherwise, the `Illegal ssml text` error is reported.
voice	String	No	The voice. The default value is xiaoyun.
format	String	No	The audio encoding format. Valid values: PCM, WAV, and MP3. Default value: `pcm`.
sample_rate	Integer	No	The audio sample rate. Default value: 16000 Hz.
volume	Integer	No	The volume. Valid values: 0 to 100. Default value: 50.
speech_rate	Integer	No	The speech rate. Valid values: -500 to 500. Default value: 0. The range [-500, 0, 500] corresponds to a speed multiplier of [0.5, 1.0, 2.0]. -500 indicates 0.5 times the default speed. 0 indicates the default speed (1.0x). The default speed varies slightly for each voice but is approximately four characters per second. 500 indicates 2.0 times the default speed. The calculation method is as follows: 0.8x speed: (1 - 1/0.8) / 0.002 = -125 1.2x speed: (1 - 1/1.2) / 0.001 = 166 Important Use a coefficient of 0.002 for speeds less than 1.0x. Use a coefficient of 0.001 for speeds greater than 1.0x. The actual algorithm result is an approximate value.
pitch_rate	Integer	No	The pitch. Valid values: -500 to 500. Default value: 0.
enable_subtitle	Boolean	No	Enables word-level timestamps. For more information about how to use this feature, see Timestamps.

Receive synthesized data
The server returns the synthesized speech as binary data. The SDK receives and processes the binary data.

End synthesis

After the speech is synthesized, the server sends a `SynthesisCompleted` event notification. The following code provides an example.

{
    "header":{
        "namespace":"SpeechLongSynthesizer",
        "name":"SynthesisCompleted",
        "status":20000000,
        "message_id":"396c80b3abf84082a48cb9e5c424****",
        "task_id":"f5805be640364cdcafc8da63e512****",
        "status_text":"Gateway:SUCCESS:Success."
    }
}

Handle synthesis failures

If the synthesis task fails due to incorrect parameters or other reasons, a `TaskFailed` notification is returned. The underlying connection is then closed. The following code provides an example.

{
   "header":{
      "namespace":"Default",
      "name":"TaskFailed",
      "status":41020001,
      "message_id":"62c126f7d9b340deb82b5b7eaca0****",
      "task_id":"4552df26d1f547aab9a2c4a94678****",
      "status_text":"TTS:TtsClientError:[tts]Engine return error code: 418"
   }
}

Service status codes

Each service response includes a `status` field, which is the service status code. The following sections describe the meanings of different status codes.

General-purpose error codes

Status code	Status message	Cause	Solution
40000000	The default client error code. This code corresponds to multiple error messages.	Invalid parameters or call logic was used.	Compare your code with the sample code in the official documentation to test and verify it.
40000001	The token 'xxx' has expired. The token 'xxx' is invalid	Invalid parameters or call logic was used. This is a general-purpose client error code that usually indicates an incorrect token, such as an expired or invalid token.	Compare your code with the sample code in the official documentation to test and verify it.
40000002	Gateway:MESSAGE_INVALID:Can't process message in state'FAILED'!	The message is invalid or incorrect.	Compare your code with the sample code in the official documentation to test and verify it.
40000003	PARAMETER_INVALID Failed to decode url params	The parameters passed by the user are incorrect. This error is common for RESTful API calls.	Compare your code with the sample code in the official documentation to test and verify it.
40000005	Gateway:TOO_MANY_REQUESTS:Too many requests!	Too many concurrent requests.	If you are using the Free Edition, you can upgrade to a commercial version to increase the concurrency. If you are already using a commercial version, you can purchase a concurrency resource plan to increase your concurrency quota.
40000009	Invalid wav header!	The message header is invalid.	If you send a WAV audio file and set the `format` parameter to `wav`, check whether the WAV header of the audio file is correct. If the header is incorrect, the server may reject the request.
40000009	Too large wav header!	The WAV header of the transmitted audio is invalid.	You can send the audio stream in a format such as PCM or OPUS. If you use the WAV format, make sure that the WAV header of the audio file contains the correct data length.
40000010	Gateway:FREE_TRIAL_EXPIRED:The free trial has expired!	The trial period has ended, and the commercial version is not activated or your account has an overdue payment.	You can log on to the console to check the service activation status and your account balance.
40010001	Gateway:NAMESPACE_NOT_FOUND:RESTful url path illegal	The operation or parameter is not supported.	Check whether the parameters passed in the call are consistent with the requirements in the official documentation. You can compare them with the error message to identify and set the correct parameters. For example, if you are using a curl command to make a RESTful API request, check whether the URL you constructed is valid.
40010003	Gateway:DIRECTIVE_INVALID:[xxx]	A general-purpose client-side error code.	This error indicates that the client passed an incorrect parameter or instruction. Detailed error messages are available for different operations. You can refer to the corresponding documentation to set the parameters correctly.
40010004	Gateway:CLIENT_DISCONNECT:Client disconnected before task finished!	The client actively terminated the connection before the request was processed.	None. Alternatively, you can close the connection after the server responds.
40010005	Gateway:TASK_STATE_ERROR:Got stop directive while task is stopping!	The client sent a message instruction that is not currently supported.	Compare your code with the sample code in the official documentation to test and verify it.
40020105	Meta:APPKEY_NOT_EXIST:Appkey not exist!	A non-existent Appkey was used.	Confirm whether a non-existent Appkey was used. You can log on to the console and view the project configuration to find the Appkey.
40020106	Meta:APPKEY_UID_MISMATCH:Appkey and user mismatch!	The Appkey and token passed in the call were not created by the same Alibaba Cloud account UID. This causes a mismatch.	Check whether you are using resources from two different accounts. Do not use an Appkey from Account A with a token generated from Account B.
403	Forbidden	The token is invalid. For example, the token does not exist or has expired.	Set a valid token. Tokens have an expiration period. You must obtain a new token before the current one expires.
41000003	MetaInfo doesn't have end point info	Failed to retrieve the routing information for this Appkey.	Check whether you are using resources from two different accounts. Do not use an Appkey from Account A with a token generated from Account B.
41010101	UNSUPPORTED_SAMPLE_RATE	The sample rate is not supported.	Real-time speech recognition currently supports only audio with a sample rate of 8000 Hz or 16000 Hz.
41040201	Realtime:GET_CLIENT_DATA_TIMEOUT:Client data does not send continuously!	Failed to retrieve data from the client due to a timeout.	When you call real-time speech recognition, the client must send data at a real-time rate and close the connection promptly after the data is sent.
50000000	GRPC_ERROR:Grpc error!	An exception caused by factors such as machine load or network issues. This error usually occurs randomly.	You can retry the call to resolve the issue.
50000001	GRPC_ERROR:Grpc error!	An exception caused by factors such as machine load or network issues. This error usually occurs randomly.	You can retry the call to resolve the issue.
52010001	GRPC_ERROR:Grpc error!	An exception caused by factors such as machine load or network issues. This error usually occurs randomly.	You can retry the call to resolve the issue.

Speech synthesis/Long text-to-speech error codes

Status code	Status message	Cause	Solution
21050000	SUCCESS	Success.	None.
21050001	RUNNING	The asynchronous long text-to-speech task is running.	You can send a GET request later to query the detection result.
21050002	QUEUEING	The asynchronous long text-to-speech task is in the queue.	Send a GET request later to query the detection result.
40000001	Gateway:ACCESS_DENIED:No privilege to this voice!	An invalid voice name was set.	Set a valid voice name based on the official documentation.
40000004	Gateway:IDLE_TIMEOUT:Websocket session is idle for too long time,the last directive is 'StartSynthesis'!	After a connection is established, no data is sent for an extended period. The server returns this error message after 10 seconds.	Close the connection promptly after the request is processed. This error may also occur when the server is under high momentary pressure and cannot return data in time. In this case, you can retry the call.
40010003	Gateway:DIRECTIVE_INVALID:No text specified!	No valid text was set for synthesis.	Set the text to be synthesized based on the sample code in the official documentation.
41020001	Speech synthesis call client-side error	Multiple error messages may be displayed. Resolve each error based on the corresponding message.	If the error message is `Engine return error code: 424.`, it indicates that the background music or concatenated recording is in an invalid format. Set the background music to a supported format as described in the documentation. If the error message is `Engine return error code:418`, it indicates that an unsupported voice name was passed. If the error message is `Engine return error code: 413`, it indicates that the SSML format is invalid. If the error message is `Request json illegal,failed to parse request.`, it indicates that the JSON format is invalid. If the error message is `SSML text length should be less than 300.`, it indicates that the synthesis text is too long. We recommend that you use the long text-to-speech API.
51020001	TTS:TtsServerError	An exception occurred due to factors such as machine load or network issues. This error is usually intermittent.	Retry the call.