Alibaba Cloud Speech Synthesis API reference-Intelligent Speech Interaction(ISI)-阿里云帮助中心

The speech synthesis service converts input text to binary audio data over a WebSocket connection.

← Back to Speech Synthesis

Billing and concurrency limits

Speech synthesis supports trial and commercial billing modes. For more information, see Free trial and Commercial Edition. To upgrade from the trial to the commercial version, see Billing.
For billing methods, see Billing.
For concurrency limits, see Concurrency and QPS.

Features

Supports PCM, WAV, and MP3 output formats.
Supports configuring the speaking rate, pitch, and volume.
Supports voices for different scenarios and styles. See Voices.
Supports synthesizing up to 300 characters per request. A Chinese character, English letter, punctuation mark, or interword space counts as one character. Content beyond 300 characters is truncated.
Input text must be UTF-8 encoded.
Supports multi-emotion voices. For usage information, see Introduction to SSML for the <emotion> tag. Tags are not counted as characters.If a rare character is mispronounced, use the SSML <phoneme> tag to specify its pinyin, or replace the character with a homophone. For more information, see Introduction to SSML.

Note

Timestamp support: The service can return the position of each Chinese character or English word in the audio. You can use the timestamps for digital-human lip synchronization and video subtitles. For more information, see Introduction to the speech synthesis timestamp feature.
Replace the original audio track in a video or audio file with a preset TTS voice:
1. Call the TTS API to generate an audio file and use the voice parameter to specify the voice. To synchronize the audio by timestamp, set enable_subtitle=true and select a voice that supports timestamps, such as siqi, siyue, or sicheng. The default voice xiaoyun does not support timestamps. Timestamps are returned only over WebSocket.
2. Use ffmpeg to merge the audio with the video:ffmpeg -i input.mp4 -i tts_output.wav -c:v copy -c:a aac -map 0:v:0 -map 1:a:0 output.mp4.
For voices intended for literature scenarios, see Long-text speech synthesis API reference.
To use the Android or iOS SDK, see Mobile SDK API reference.

Intelligent access to the nearest region

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

For end users, use intelligent access to the nearest region. The domain name resolves to the nearest regional server based on the client's location. For example, a request from Beijing resolves to the same server as the endpoint nls-gateway-cn-beijing.aliyuncs.com.

Endpoint

Access type	Description	URL
Internet access (China (Shanghai) by default)	All servers can access the service over the Internet. The SDK uses the Internet endpoint 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 internal-network access	ECS instances in the China (Shanghai), China (Beijing), and China (Shenzhen) regions can use the internal endpoints. ECS instances in the classic network cannot access AnyTunnel. To access AnyTunnel over an internal network, use a virtual private cloud (VPC). Note Internal-network access does not incur Internet data transfer fees for ECS instances. For information about ECS network types, see What is VPC.	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 shows the WebSocket interaction flow. For the RESTful API interaction flow, see RESTful API.
In addition to the audio stream, each server response contains the task_id parameter in the header. The parameter uniquely identifies the request.
To play the audio stream in real time, use a player that supports streaming playback, such as ffmpeg, pyaudio for Python, AudioFormat for Java, or MediaSource for JavaScript.

Authenticate
The client uses a token for authentication when it establishes a WebSocket connection to the server. For information about how to obtain a token, see Obtain a token.

Start synthesis

The client sends a speech synthesis request and configures the request parameters. The following table describes the parameters.

Parameter	Type	Required	Description
appkey	String	Yes	consoleThe appkey of the project created in the console.
text	String	Yes	The text to synthesize. The text must be UTF-8 encoded and cannot exceed 300 characters. Separate English words with spaces. Note To synthesize speech with an emotion-supported voice, add the SSML emotion tag to the text parameter. For more information, see Introduction to SSML. Only voices that support multiple emotions can use the <emotion> tag. Otherwise, the request returns the error Illegal ssml text.
voice	String	No	The voice. Default: `xiaoyun`.
format	String	No	The audio format. Valid values: .pcm, .wav, and .mp3. Default: `pcm`.
sample_rate	Integer	No	The audio sample rate. Default: 16000 Hz.
volume	Integer	No	The volume. Valid values: 0 to 100. Default: 50.
speech_rate	Integer	No	The speaking rate. Valid values: -500 to 500. Default: 0. The values [-500, 0, 500] correspond to the speed multipliers [0.5, 1.0, 2.0]. -500 specifies 0.5 times the default speaking rate. 0 specifies the default speaking rate. The default rate varies by voice and is approximately four Chinese characters per second. 500 specifies twice the default speaking rate. Use the following formulas: 0.8× speed: (1-1/0.8)/0.002 = -125 1.2× speed: (1-1/1.2)/0.001 = 166 Note For a speed multiplier below 1, use the coefficient 0.002. For a speed multiplier above 1, use the coefficient 0.001. The algorithm rounds the result to an approximate value.
pitch_rate	Integer	No	The pitch. Valid values: -500 to 500. Default: 0.
enable_subtitle	Boolean	No	Specifies whether to enable character-level timestamps. For more information, see Introduction to the speech synthesis timestamp feature.

Receive synthesized audio
The server returns synthesized audio as a binary stream. Use the SDK to receive and process it.

Complete synthesis

After synthesis is complete, the server sends a SynthesisCompleted event, as shown in the following example.

{
    "header": {
        "message_id": "05450bf69c53413f8d88aed1ee60****",
        "task_id": "640bc797bb684bd6960185651307****",
        "namespace": "SpeechSynthesizer",
        "name": "SynthesisCompleted",
        "status": 20000000,
        "status_message": "GATEWAY|SUCCESS|Success."
    }
}

Note

The sample saves the synthesized audio to a file. For lower playback latency, use streaming playback to play the audio as it arrives.

Handle synthesis failures

If synthesis fails because of invalid parameters or another error, the client receives a TaskFailed event, as shown in the following example. The underlying connection is closed after the event is received.

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

Voices

Name	Voice parameter	Type	Scenario	Supported language	Sample rate (Hz)	Timestamp support	Erhua support	Voice quality
Abin	abin	Guangdong-accented Mandarin	Conversational digital human	Chinese or bilingual Chinese and English	8K/16K/24K/48K	No	No	Standard
Zhixiaobai	zhixiaobai	Mandarin female	Conversational digital human	Chinese or bilingual Chinese and English	8K/16K/24K/48K	No	Yes	Standard
Zhixiaoxia	zhixiaoxia	Mandarin female	Conversational digital human	Chinese or bilingual Chinese and English	8K/16K/24K/48K	No	Yes	Standard
Zhixiaomei	zhixiaomei	Mandarin female	Live-streaming digital human	Chinese or bilingual Chinese and English	8K/16K/24K	Yes	Yes	Standard
Zhigui	zhigui	Mandarin female	Live-streaming digital human	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Zhishuo	zhishuo	Mandarin male	Customer-service digital human	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Aixia	aixia	Amiable female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	Yes	Standard
Cally	cally	American English female	English conversational digital human	English only	8K/16K	Yes	Yes	Standard
Zhifeng Emo	zhifeng_emo	Multi-emotion male	General	Chinese or bilingual Chinese and English	8K/16K/24K	Yes	Yes	Standard
Zhibing Emo	zhibing_emo	Multi-emotion male	General General scenarios	Chinese only Chinese-only scenarios	8K/16K/24K	Yes Yes	Yes	Standard
Zhimiao Emo	zhimiao_emo	Multi-emotion female	Chinese and English	Chinese and English	8K/16K	Yes	Yes	Standard
Zhimi Emo	zhimi_emo	Multi-emotion female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Standard
Zhiyan Emo	zhiyan_emo	Multi-emotion female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Standard
Zhibei Emo	zhibei_emo	Multi-emotion child	General	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Standard
Zhitian Emo	zhitian_emo	Multi-emotion female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Standard
Xiaoyun	xiaoyun	Standard female	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K	No	No	Lite
Xiaogang	xiaogang	Standard male	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K	No	No	Lite
Ruoxi	ruoxi	Gentle female	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K/24K	No	No	Standard
Siqi	siqi	Gentle female	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K/24K	Yes	No	Standard
Sijia	sijia	Standard female	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K/24K	No	No	Standard
Sicheng	sicheng	Standard male	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K/24K	Yes	No	Standard
Aiqi	aiqi	Gentle female	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aijia	aijia	Standard female	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aicheng	aicheng	Standard male	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aida	aida	Standard male	All scenarios	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Ning'er	ninger	Standard female	All scenarios	Chinese only	8K/16K/24K	No	No	Standard
Ruilin	ruilin	Standard female	All scenarios	Chinese only	8K/16K/24K	No	No	Standard
Siyue	siyue	Gentle female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K/24K	Yes	No	Standard
Aiya	aiya	Harsh female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aimei	aimei	Sweet female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aiyu	aiyu	Natural female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aiyue	aiyue	Gentle female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Aijing	aijing	Harsh female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Xiaomei	xiaomei	Sweet female	Customer service	Chinese or bilingual (Chinese and English)	8K/16K/24K	No	No	Standard
Aina	aina	Female, Zhejiang accent	Customer service	Chinese only	8K/16K	Yes	No	Standard
Yina	yina	Female, Zhejiang accent	Customer service	Chinese only	8K/16K/24K	No	No	Standard
Sijing	sijing	Harsh female	Customer service	Chinese only	8K/16K/24K	Yes	No	Standard
Sitong	sitong	Child voice	Child voice scenarios	Chinese only	8K/16K/24K	No	No	Standard
Xiaobei	xiaobei	Little girl voice	Child voice scenarios	Chinese only	8K/16K/24K	Yes	No	Standard
Aitong	aitong	Child voice	Child voice scenarios	Chinese only	8K/16K	Yes	No	Standard
Aiwei	aiwei	Little girl voice	Child voice scenarios	Chinese only	8K/16K	Yes	No	Standard
Aibao	aibao	Little girl voice	Child voice scenarios	Chinese only	8K/16K	Yes	No	Standard
Harry	harry	Male, British accent	English only	English only	8K/16K	No	No	Standard
Abby	abby	Female, American accent	English only	English only	8K/16K	Yes	No	Standard
Andy	andy	Male, American accent	English only	English only	8K/16K	Yes	No	Standard
Eric	eric	Male, British accent	English only	English only	8K/16K	Yes	No	Standard
Emily	emily	Female, British accent	English only	English only	8K/16K	Yes	No	Standard
Luna	luna	Female, British accent	English only	English only	8K/16K	Yes	No	Standard
Luca	luca	Male, British accent	English only	English only	8K/16K	Yes	No	Standard
Wendy	wendy	Female, British accent	English only	English only	8K/16K/24K	No	No	Standard
William	william	Male, British accent	English only	English only	8K/16K/24K	No	No	Standard
Olivia	olivia	Female, British accent	English only	English only	8K/16K/24K	No	No	Standard
Shanshan	shanshan	Female, Cantonese	Dialect scenarios	Cantonese (simplified) and bilingual (Cantonese and English)	8K/16K/24K	No	No	Standard
Aiyuan	aiyuan	Caring female	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aiying	aiying	Cute child	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aixiang	aixiang	Resonant male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aimo	aimo	Emotional male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aiye	aiye	Young male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aiting	aiting	Radio female	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aifan	aifan	Emotional female	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Lydia	lydia	Female, bilingual (Chinese and English)	English only	English only	8K/16K	Yes	No	Standard
Chuangirl	chuangirl	Sichuan-accented female	Dialect	Chinese or bilingual Chinese and English	8K/16K	No	No	Standard
Aishuo	aishuo	Natural male	Customer service	Chinese or bilingual (Chinese and English)	8K/16K	Yes	No	Standard
Qingqing	qingqing	Female, Taiwanese	Dialect scenarios	Chinese only	8K/16K	No	No	Standard
Cuijie	cuijie	Female, Northeastern Mandarin	Dialect scenarios	Chinese only	8K/16K	Yes	Yes	Standard
Xiaoze	xiaoze	Male, Hunan accent	Dialect scenarios	Chinese only	8K/16K	No	No	Standard
Ainan	ainan	Advertising male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aihao	aihao	Information male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aiming	aiming	Humorous male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aixiao	aixiao	Information female	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aichu	aichu	Food-documentary male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Aiqian	aiqian	Information female	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Tomoka	tomoka	Japanese female	Multilingual	Japanese only	8K/16K	Yes	No	Standard
Tomoya	tomoya	Japanese male	Multilingual	Japanese only	8K/16K	Yes	No	Standard
Annie	annie	American English female	English	English only	8K/16K	Yes	No	Standard
Aishu	aishu	Information male	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Airu	airu	News female	Literature	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Premium
Jiajia	jiajia	Cantonese female	Dialect	Simplified Cantonese or bilingual Cantonese and English	8K/16K	Yes	No	Standard
Indah	indah	Indonesian female	Multilingual	Indonesian only	8K/16K	No	No	Standard
Taozi	taozi	Cantonese female	Dialect	Simplified Cantonese or bilingual Cantonese and English	8K/16K	Yes	No	Standard
Guijie	guijie	Friendly female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Stella	stella	Intellectual female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Stanley	stanley	Calm male	General	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Kenny	kenny	Calm male	General	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Rosa	rosa	Natural female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Farah	farah	Malay female	Multilingual	Malay only	8K/16K	No	No	Standard
Mashu	mashu	Children's drama male	General	General	8K/16K	Yes	No	Standard
Zhiqi	zhiqi	Gentle female	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhichu	zhichu	Food-documentary male	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	Yes	Premium
Xiaoxian	xiaoxian	Friendly female	Live streaming	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Yuer	yuer	Children's drama female	General	Chinese only	8K/16K	Yes	No	Standard
Maoxiaomei	maoxiaomei	Energetic female	Live streaming	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Zhixiang	zhixiang	Resonant male	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhijia	zhijia	Standard female	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhinan	zhinan	Advertising male	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhiqian	zhiqian	Information female	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhiru	zhiru	News female	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhide	zhide	News male	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K/24K/48K	Yes	No	Premium
Zhifei	zhifei	Passionate narration	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Premium
Aifei	aifei	Passionate narration	Live streaming	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Yaqun	yaqun	Retail announcement	Live streaming	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Qiaowei	qiaowei	Retail announcement	Live streaming	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Dahu	dahu	Northeastern Mandarin male	Dialect	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
ava	ava	American English female	English	English only	8K/16K	Yes	No	Standard
Zhilun	zhilun	Suspense narration	Ultra-HD	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Premium
Ailun	ailun	Suspense narration	Live streaming	Chinese or bilingual Chinese and English	8K/16K	Yes	Yes	Standard
Jielidou	jielidou	Soothing child	Child voice	Chinese only	8K/16K	Yes	Yes	Standard
Zhiwei	zhiwei	Young girl	Ultra-HD	Chinese only	8K/16K/24K/48K	Yes	No	Premium
Laotie	laotie	Northeastern Mandarin male	Live streaming	Chinese only	8K/16K	Yes	Yes	Standard
Laomei	laomei	Vendor-call female	Live streaming	Chinese only	8K/16K	Yes	Yes	Standard
Aikan	aikan	Tianjin-accented male	Dialect	Chinese only	8K/16K	Yes	Yes	Standard
Tala	tala	Filipino female	Multilingual	Filipino only	8K/16K	No	No	Standard
Zhitian	zhitian	Sweet female	General	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Premium
Zhiqing	zhiqing	Taiwan-accented female	Dialect	Chinese only	8K/16K	Yes	No	Premium
Tien	tien	Vietnamese female	Multilingual	Vietnamese only	8K/16K	No	No	Standard
Becca	becca	American English customer-service female	American English	English only	8K/16K	No	No	Standard
Kyong	Kyong	Korean female	Korean	Korean	8K/16K	No	No	Standard
masha	masha	Russian female	Russian	Russian	8K/16K	No	No	Standard
camila	camila	Spanish female	Spanish	Spanish	8K/16K	No	No	Standard
perla	perla	Italian female	Italian	Italian	8K/16K	No	No	Standard
Zhimao	zhimao	Mandarin female	Live streaming	Chinese	8K/16K	Yes	No	Standard
Zhiyuan	zhiyuan	Mandarin female	General	Chinese	8K/16K	Yes	No	Standard
Zhiya	zhiya	Mandarin female	Customer service	Chinese	8K/16K	Yes	No	Standard
Zhiyue	zhiyue	Mandarin female	General	Chinese	8K/16K	Yes	No	Standard
Zhida	zhida	Mandarin male	General	Chinese or bilingual Chinese and English	8K/16K	Yes	No	Standard
Zhistella	zhistella	Mandarin female	General	Chinese	8K/16K	Yes	No	Standard
Kelly	kelly	Hong Kong Cantonese female	Dialect	Hong Kong Cantonese	8K/16K	Yes	No	Standard
clara	clara	French female	General	French	8K/16K	No	No	Standard
hanna	hanna	German female	General	German	8K/16K	No	No	Standard
waan	waan	Thai female	General	Thai	8K/16K	No	No	Standard
betty	betty	American English female	General	American English	8K/16K	Yes	No	Standard
beth	beth	American English female	General	American English	8K/16K	Yes	No	Standard
cindy	cindy	American English female	General	American English	8K/16K	Yes	No	Standard
donna	donna	American English female	General	American English	8K/16K	Yes	No	Standard
eva	eva	American English female	General	American English	8K/16K	Yes	No	Standard
brian	brian	American English male	General	American English	8K/16K	Yes	No	Standard
david	david	American English male	General	American English	8K/16K/24K	Yes	No	Standard
abby_ecmix	abby_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
annie_ecmix	annie_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
andy_ecmix	andy_ecmix	American English male	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
ava_ecmix	ava_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
betty_ecmix	betty_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
beth_ecmix	beth_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
brian_ecmix	brian_ecmix	American English male	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
cindy_ecmix	cindy_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
cally_ecmix	cally_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
donna_ecmix	donna_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
david_ecmix	david_ecmix	American English male	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard
eva_ecmix	eva_ecmix	American English female	General	English or bilingual English and Chinese	8K/16K/24K	Yes	No	Standard

Multi-emotion voice support

Only multi-emotion voice models support emotion selection. Supported emotions vary by voice and can include neutral, happy, angry, sad, fear, hate, surprise, arousal, serious, disgust, jealousy, embarrassed, frustrated, affectionate, gentle, newscast, customer-service, story, and living.

Voice name	Voice parameter	Emotion category
Zhifeng (multi-emotion)	zhifeng_emo	angry, fear, happy, neutral, sad, surprise
Zhibing (multi-emotion)	zhibing_emo	angry, fear, happy, neutral, sad, surprise
Zhimiao (multi-emotion)	zhimiao_emo	serious, sad, disgust, jealousy, embarrassed, happy, fear, surprise, neutral, frustrated, affectionate, gentle, angry, newscast, customer-service, story, living
Zhimi (multi-emotion)	zhimi_emo	angry, fear, happy, hate, neutral, sad, surprise
Zhiyan (multi-emotion)	zhiyan_emo	neutral, happy, angry, sad, fear, hate, surprise, arousal
Zhibei (multi-emotion)	zhibei_emo	neutral, happy, angry, sad, fear, hate, surprise
Zhitian (multi-emotion)	zhitian_emo	neutral, happy, angry, sad, fear, hate, surprise

Status codes

Each response contains a status field that indicates the service status code. The following tables describe the 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 `format` to `wav`, make sure that the WAV header is valid. Otherwise, the server may reject the file.
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. On the Service Management and Activation page of the Intelligent Speech Interaction console, verify that the service used by the API or SDK is upgraded to the Commercial Edition. Speech synthesis and streaming text-to-speech are separate services and must be upgraded to the Commercial Edition separately. Upgrading one service does not upgrade the other. Make sure that the SDK matches the activated service. For example, before you use the streaming text-to-speech SDK, upgrade streaming text-to-speech to the Commercial Edition.
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 implementation with the sample code in the documentation. If the message `empty body data` is returned, troubleshoot the issue as follows: Check how the audio is passed. If you use a URL, make sure that the URL is valid and the audio file has been generated. If you use a binary stream, compare the original audio data with the data sent by the client and forwarded by the server. The data must be non-empty and identical. Run the official sample after replacing AccessKeyId, AccessKeySecret, and Appkey with your credentials to rule out an implementation issue. Use fixed test parameters and a fixed audio source, such as a fixed OSS URL, to reproduce the issue and determine whether the cause is the network, data preparation, or the API call.
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 speech synthesis error codes

Status code	Status message	Cause	Solution
40000001	Gateway:ACCESS_DENIED:No privilege to this voice!	An incorrect speaker name was set.	You can refer to the official documentation to set the correct speaker.
40000004	Gateway:IDLE_TIMEOUT:Websocket session is idle for too long time,the last directive is 'StartSynthesis'!	After a connection is established, the server returns this error message if no data is sent for more than 10 seconds.	Close the connection promptly after the request is processed. This error may also occur if the server is under high instantaneous pressure and cannot return data in time. In this case, you can retry the request to resolve the issue.
40010003	Gateway:DIRECTIVE_INVALID:No text specified!	No valid text for synthesis was set.	You can refer to the sample code in the official documentation to set the text for synthesis.
41020001	Speech synthesis client error	Multiple error messages may be returned. Adjust your code based on the specific error message.	The message `Engine return error code: 424.` indicates that the background music or concatenated recording has an invalid format. Configure the background audio as described in the documentation. The message `Engine return error code:418` indicates that the specified voice is unsupported. If this error is returned for a CosyVoice-V2 voice, use the WebSocket endpoint of the China (Beijing) region (`wss://nls-gateway-cn-beijing.aliyuncs.com/ws/v1`). CosyVoice large-model voices are available only in the China (Beijing) region. A cloned VoiceName does not support the `enable_subtitle` timestamp feature. Only some official long-text voices, such as voices whose names start with long, support this feature. The message `Engine return error code: 413` indicates that SSML tags of the same type are nested. Tags of the same type, such as `s, p, and break`, cannot be nested. Tags of different types can be nested. Place tags of the same type at the same level. For example, do not nest a `p` tag inside an `s` tag within `speak`. Instead, place separate `s` tags for the text segments at the same level within `speak`. The message `Request json illegal,failed to parse request.` indicates that the JSON payload is invalid. The message `SSML text length should be less than 300.` indicates that the synthesis text is too long. Use long-text speech synthesis.
51020001	TTS:TtsServerError	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.