Offline speech synthesis API reference-Intelligent Speech Interaction(ISI)-阿里云帮助中心

Offline speech synthesis converts text into natural, fluent speech using a local speech synthesis model on a device. This feature works in environments with poor or no network connectivity.

Features

Offline speech synthesis includes the following features. Multiple instance calls are not supported.

You can adjust the speech rate, pitch, and volume.
This feature is suitable for scenarios such as in-car navigation, smart hardware, audiobook reading, and accessibility announcements.
It integrates as a software development kit (SDK) and supports multiple hardware platforms.
Billing is based on the number of activated devices, which provides cost flexibility and control.
A variety of voice options are available.

Prerequisites

The SDK must be activated. For more information, see Activate the service.

Voice packages

Name	voice parameter value	Type	Scenarios	Supported languages	Supported sample rates (Hz)	Notes	Download link
Aijia	aijia	Standard female voice	General	Supports Chinese and mixed Chinese-English scenarios.	24K	Premium Edition	Download voice package
Aicheng	aicheng	Warm male voice	General scenarios	Supports Chinese and mixed Chinese-English scenarios.	24K	Premium Edition	Download voice package
Aiqi	aiqi	Gentle female voice	General	Supports Chinese scenarios.	24K	Premium Edition	Download voice package
Aida	aida	Standard male voice	General	Supports Chinese scenarios.	24 K	Premium Edition	Download voice package
Aihao	aihao	News-style male voice	Literature	Supports Chinese scenarios.	24 K	Premium Edition	Download voice package
Aishuo	aishuo	Natural male voice	Customer service	Supports Chinese scenarios.	24K	Premium Edition	Download voice package
Aiying	aiying	Cute child voice	Literature	Supports Chinese and mixed Chinese-English scenarios.	24 K	Premium Edition	Download voice package
Aitong	aitong	Child voice	Child voice scenarios	Supports only Chinese scenarios.	24K	Premium Edition	Download voice package
Abby	abby	American English female voice	English scenarios	Supports only English scenarios.	24 K	Premium Edition	Download voice package
Andy	andy	American English male voice	English scenarios	Supports only English scenarios.	24K	Premium Edition	Download voice package
Annie	annie	American English female voice	English scenarios	Supports only English scenarios.	24 kHz	Premium Edition	Download voice package
Xiaoyun	xiaoyun	Standard female voice	General	Supports Chinese and mixed Chinese-English scenarios.	16 kHz	Standard Edition	Download voice package
Xiaoda	xiaoda	Standard male voice	General	Chinese and mixed Chinese-English scenarios	16 kHz	Standard Edition	Download voice package
Xiaogang	xiaogang	Warm male voice	General	Chinese and mixed Chinese-English scenarios	16K	Standard Edition	Download voice package
Xiaoqi	xiaoqi	Gentle female voice	General	Chinese and mixed Chinese-English scenarios	16 kHz	Standard Edition	Download voice package
Xiao Xia	xiaoxia	Natural female voice	Customer service	Chinese and mixed Chinese-English scenarios	16 kHz	Standard Edition	Download voice package

Sequence diagram

Activation and initialization parameters

This section describes the parameters for activating and initializing the offline text-to-speech (TTS) SDK. These parameters include authentication credentials, the workspace path, and the log storage path.

Important

After you set and enable the initialization parameters, you cannot change them.

Parameter	Type	Description	Required
ak_id	string	The AccessKey ID. For more information about how to obtain an AccessKey ID, see Activate the service.	Yes
ak_secret	string	The AccessKey secret. For more information about how to obtain an AccessKey secret, see Activate the service.	Yes
app_key	string	The AppKey of the project. It is automatically generated after the project is created. In the navigation bar of the console, click All Projects to view the AppKey.	Yes
sdk_code	string	The product code. Standard Edition sdk_code: software_nls_tts_offline_standard Premium Edition sdk_code: software_nls_tts_offline	Yes
device_id	string	The device ID. Note The device_id must be globally unique within an AppKey.	Yes
workspace	string	The resource path.	Yes
mode_type	string	Set to "0" to initialize the local engine.	Yes
debug_path	string	The log storage path. Note Including this field enables log storage. To disable log storage, set the debug_level parameter to 5 in the dynamic parameter settings. Log files are stored in append mode.	No
enable_et	string	Valid values: true and false. Set to false to disable data reporting. Data reporting is enabled by default. For more information about data reporting, see How does the SDK perform data reporting?	No
enable_ntp	string	Valid values: true and false. Set to false to disable NTP. NTP is enabled by default. The NTP feature is used to get the Alibaba Cloud time for authentication. For more information, see What is the purpose of NTP?	No
enable_low_precision	string	Valid values: true and false. The default value is false, which indicates high-precision mode. If you set this parameter to true, low-precision mode is used. This reduces the computational load but slightly degrades audio quality.	No
authspace	string	For debugging purposes, you can generate the authentication file in a fixed directory, such as "/storage/emulated/0/tts". Make sure the directory exists and has read and write permissions. This avoids re-authentication when you uninstall and reinstall the app. If you do not set this parameter, the authentication file is stored in the workspace directory.	No
extend	string	Extended field (JSON).	No

Dynamic parameters

The in property indicates a parameter that you can set for the SDK. You can dynamically set in parameters using `setparamTts`. Android is used as an example. The new setting takes effect for the next request.
The out property indicates a parameter that you can retrieve from the SDK. You can retrieve out parameters using `getparamTts`.

Parameter	Type	Property	Value	Meaning
extend_font_name	string	in	full_path	Switches the voice. The full path of the voice package resource, such as /sdcard/xiaoyun.
speed_level	string	in\|out	(0, 2]. Default: 1.0.	The speech rate. A larger value indicates a faster rate. If the set value is out of range, the default value is used.
pitch_level	string	in\|out	[-500, 500]. Default: 0.	The pitch. A larger value indicates a higher pitch. If the set value is out of range, the default value is used.
volume	string	in\|out	(0, 2]. Default: 1.0.	The volume. A larger value indicates a higher volume. If the set value is out of range, the default value is used. Important To avoid clipping noise, set the value to 1.5 or lower.
callback_raw_data	string	in	0 or 1. Default: 0.	0: Returns the raw data in the callback. 1: Returns the decoded data in the callback. For example, if the raw synthesized data is in MP3 format, the callback returns PCM data.
debug_level	string	in\|out	0, 1, 2, 3, 4, 5	Log level 0: verbose (no filter) 1: debug 2: info 3: warning 4: error 5: disable logging
error_msg	string	out	Error message	When an API call fails, this parameter provides a detailed error message. Consider this information when you implement data reporting. It is an effective way to analyze issues.
model_sample_rate	string	out	16000 or 24000	The sample rate of the audio data. The typical value is 24000.
enable_callback_vol	string	in	0 or 1. Default: 0.	0: Does not return the volume in the callback. 1: Returns the volume in the callback. This consumes some resources. Disable it if not necessary.
enable_monopoly	string	in	0 or 1. Default: 1.	0: Enables non-exclusive mode. The synthesis speed decreases, and the peak CPU usage drops. 1: Enables exclusive mode. The synthesis speed is fast, and the peak CPU usage is relatively high.

Performance metrics

Note

The Chinese voice Aicheng is used as an example. Metrics may vary slightly for different voices.

Item	Metric
CPU	Model	Hardware specifications	Initialization time	CPU (synthesis state: single core)
	Redmi 6A	CPU: MediaTek Helio A22 2 GHz RAM: 2 GB OS: Android 9.0	273 ms	19%
	Huawei P10	CPU: HiSilicon Kirin 960 2.4 GHz RAM: 4 GB OS: Android 7.0	178 ms	12%
	Huawei P40	CPU: HiSilicon Kirin 990 2.86 GHz RAM: 6 GB OS: Android 10.0	67 ms	8.2%
ROM	SDK package size Depends on the number and size of voice packages.
RAM	21.73 M

Error codes

If a speech synthesis error occurs, the SDK reports a TTS_EVENT_ERROR event and provides an error code. The following tables describe the error 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 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.	If the message `Engine return error code: 424.` is returned, the background music or concatenated recording does not conform to the required format. You can set the correct background music as described in the documentation. If the message `Engine return error code:418` is returned, an unsupported speaker name was passed. If the message `Engine return error code: 413` is returned, the SSML format used is incorrect. If the message `Request json illegal,failed to parse request.` is returned, the passed JSON format is invalid. If the message `SSML text length should be less than 300.` is returned, the synthesis text is too long. You must use the long-text speech synthesis operation.
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.

Speech synthesis/Offline speech synthesis

SDK-related

Status code	Status message	Cause	Solution
140000	TTS_CREATE_FAILED	Engine initialization failed.	The resource path is incorrect or a resource file is abnormal. This fault is often accompanied by the error code TTS_ASSETPATH_INVALID. Review the log to confirm. Ensure the provided resource path is valid and all resource files are complete.
140001	TTS_ENGINE_INVALID	The engine is not initialized.	The current TTS instance is not created. Check if the initialization API has been called.
140002	TTS_TEXT_ERROR	The text is invalid, for example, empty.	Check the SDK log to confirm that the file is invalid. Ensure that the input text is valid.
140003	TTS_MALLOC_FAILED	Memory allocation failed.	Out of memory. Ensure enough memory is available.
140005	TTS_ASSETPATH_INVALID	The resource path is empty.	The resource path is incorrect or a resource file is abnormal. Check the logs to confirm the fault. Ensure the provided resource path is valid and all resource files are complete.
140006	TTS_HANLDE_INVALID	The processing thread does not exist.	You can release TTS and then retry.
140007	TTS_CREATE_HANLDE_FAILED	Failed to create the processing thread.	Check the error message in the log to identify the problem.
140008	TTS_AUTH_FAILED	Authentication failed. The SDK cannot be used.	Check that the akId, akSecret, and appkey are correct. Review the error message in the log for details. The issue may be that offline authentication is not enabled or that your quota is exhausted.
140011	TTS_OPERATE_INVALID	Invalid operation.	The current processing thread is in an invalid state. This can occur if a call, such as `pause`, is made before initialization. Ensure that calls are valid for the current state.
140012	TTS_OPEN_FILE_FAILED	Failed to open the file.	Failed to open the wav debug file or the log file. Check the error message in the log for details.
140013	TTS_STATE_INVALID	State machine verification failed.	The method call is invalid for the current state machine. This can occur if a method, such as `pause`, is called before initialization. Ensure that method calls are valid for the current state.
140014	TTS_SYNTHESIZER_INIT_ERROR	Synthesizer initialization failed.	Synthesizer creation failed, mainly due to out of memory.
140015	TTS_SYNTHESIZER_RELEASE_ERROR	Synthesizer release failed.	The synthesizer failed to release. Check the logs to pinpoint the cause.
140016	TTS_SYNTHESIZER_FAILED	Synthesis failed.	A state fault occurred during pre-playback. Check the logs to pinpoint the cause.
140017	TTS_WAIT_TIMEOUT	Timeout exit.	If a timeout occurs while waiting for a status, check the logs for details.
140018	TTS_CLOSED	The TTS part of the code was not compiled.	The current SDK does not include the TTS feature. Switch to the correct SDK.

Parameter configuration-related

Status code	Status message	Cause	Solution
140100	TTS_PARAM_INVALID	Invalid parameter.	An invalid input parameter was provided during initialization or when setting parameters. For example, the workspace, callback, taskId, or text is empty. Check the logs to locate the specific error.
140101	TTS_PARAM_VALUE_INVALID	Invalid parameter value.	Invalid input parameter. Check the logs to pinpoint the error.
140102	TTS_CFG_OPEN_FAILED	Failed to open the configuration file.	The resource path is incorrect or the resource file is abnormal. Check the log to confirm. Ensure the resource path is valid and all resource files are complete.

Audio processing

Status code	Status message	Cause	Solution
140200	TTS_AM_CREATE_FAILED	Player creation failed.	Creation of the SDK's internal audio manager failed.
140210	TTS_AM_OPEN_FAILED	Player open failed.	The SDK internal audio manager failed to open. Check the logs to pinpoint the issue.
140210	TTS_DECODER_INIT_FAILED	Audio decoder initialization failed.	The audio decoder, possibly an MP3 decoder, failed to initialize. Check the logs to pinpoint the cause.
140211	TTS_DECODER_MALLOC_FAILED	Audio decoder failed to allocate memory.	Out of memory. Ensure enough memory is available.
140212	TTS_DECODER_INPUT_TOO_MANY	Too much data was input at once and will be discarded.	Check the log to identify the specific issue. The maximum data size for a single input is 2000.
140213	TTS_DECODER_OUTPUT_TOO_MANY	Too much data was output, exceeding the cache, and will be lost.	Check the logs for detailed information.
140220	TTS_AP_INIT_FAILED	Audio processing unit (audioplayer) failed to open.	This error is typically returned with other AP ErrorCodes. Check the logs for more details.
140221	TTS_AP_START_FAILED	Error starting ap.	Check the logs to pinpoint the issue.
140222	TTS_AP_MALLOC_FAILED	Audioplayer failed to allocate memory.	Out of memory. Ensure there is enough memory to run.
140231	TTS_BGM_DECODE_INVALID	Decoder initialization failed.	Check the logs to confirm if the decoder is initialized.
140233	TTS_BGM_MALLOC_FAILED	Memory allocation failed.	Out of memory. Ensure there is enough memory to run.
140237	TTS_BGM_PARAM_INVALID	Background music parameter setting error.	Confirm the parameter settings are correct. Check the log to find the problem. Look for the bgm value:.

Cache-related

Status code	Status message	Cause	Solution
140300	TTS_CACHE_INIT_FAILED	Failed to initialize cache.	This error is often accompanied by the TTS_CACHE_PATH_INVALID error code. This may indicate an invalid storage path. Check the logs for details.
140302	TTS_CACHE_CMD_ERROR	The cache command is not standard.	Check the returned error message and log to pinpoint the fault.
140308	TTS_CACHE_PATH_INVALID	Failed to create the cache path.	Check the returned error message and log to locate the fault.
140309	TTS_CACHE_LIST_CREATE_FAILED	Failed to create the cache list.	Check the returned fault message and log for details.
140311	TTS_CACHE_TOO_MANY	Too much cache.	View the logs for details.
140312	TTS_CACHE_PARAM_INVALID	Parameter error.	Check the returned error message and log for details.
140313	TTS_CACHE_RECORDING_OPEN_FAILED	Error opening local file.	The file permissions or path might be incorrect. Check the logs for details.

Font delivery-related

Status code	Status message	Cause	Solution
140351	TTS_FONT_INITLIST_FAILED	Initialize the fontlist manager.	Out of memory. Ensure there is enough memory to run.
140352	TTS_FONT_INITLIST_INVALID	The fontlist manager is not initialized.	Out of memory. Ensure sufficient memory is available to run.
140353	TTS_FONT_CMD_INVALID	The command format is incorrect.	Check the returned fault messages and logs to identify the issue.
140354	TTS_FONT_RESPONSE_ERROR	The server returned an incorrect format.	Check the returned error messages and logs to pinpoint the issue.
140350	TTS_FONT_RESPONSELIST_ERROR	The fontlist request to the server returned an incorrect format.	Check the returned error message and log to locate the fault.
140356	TTS_FONT_GET_FONTLIST_FAILED	Failed to get the fontlist.	Check the returned error messages and logs to pinpoint the error.
140358	TTS_FONT_LOCALMSG_ERROR	Failed to parse the local list file.	You can check the returned error messages and logs to pinpoint the problem.
140359	TTS_FONT_LOCALFILE_ERROR	Failed to save the current list file.	Check the returned error messages and logs to pinpoint the problem.
140360	TTS_FONT_CLOUDMSG_ERROR	Failed to parse the cloud list.	Check the returned error messages and logs to locate the problem.

Local engine-related

Status code	Status message	Cause	Solution
140900	TTS_LOCAL_CRE_ENGINE_ERROR	Local engine initialization failed.	An internal error occurred in the local DPI engine. Check other error messages in the log to diagnose the fault.
140901	TTS_LOCAL_ENGINE_INVALID	The local engine is not initialized.	Check if TTS is initialized. Review the returned error messages and logs for details.
140902	TTS_LOCAL_ASSET_ERROR	Local resource verification failed.	The local engine failed to validate the resource path. Check the log for details.
140903	TTS_LOCAL_CRE_TASK_ERROR	Failed to create a local task.	You can check the logs to locate the specific issue.
140905	TTS_LOCAL_START_FAILED	Failed to start local synthesis.	View the logs to pinpoint the issue.
140906	TTS_LOCAL_OPERATION_FAILED	Local operation failed, for example, the local task does not exist or there is a default error.	View the logs to pinpoint details.
140907	TTS_LOCAL_SWITCH_FONT_FAILED	Failed to switch speaker.	Review the logs for details.
140908	TTS_LOCAL_GET_SAMPLERATE_FAILED	Failed to get the speaker's sample rate.	Check the logs to pinpoint the issue.
140909	TTS_LOCAL_ADD_FRONT_END_FAILED	Failed to add speaker.	Check the logs for details.
140910	TTS_LOCAL_VOICE_PATH_INVALID	The local speaker file does not exist or file authentication failed.	Check the logs to pinpoint the cause.
140911	TTS_LOCAL_VOICE_MISMATCH	Local speaker file mismatch.	Check the logs for details.

Cloud engine-related

Status code	Status message	Cause	Solution
141000	TTS_CLOUD_CREATE_FAILED	Cloud engine initialization failed.	View the logs for detailed information.
141004	TTS_CLOUD_START_FAILED	Cloud request failed.	This issue is typically caused by a network connection failure or invalid parameters for the Appkey, Token, or URL. Check the logs to pinpoint the exact cause.
141007	TTS_CLOUD_NETWORK_BROKEN	The network is poor.	If the network connection is poor, switch to a different network environment and try again.
141008	TTS_CLOUD_SSL_CONNECT_FAILED	SSL connection failed. Check whether the sent parameters are correct.	SSL connection failed. Check the send parameters. Review the logs for details.
141009	TTS_CLOUD_HTTP_CONNECT_FAILED	HTTP connection failed. Check whether the sent parameters are correct.	HTTP connection failed. Check the sent parameters. Review the logs for details.
141010	TTS_CLOUD_DNS_FAILED	Connection failed, DNS failed.	Connection failed. DNS failed. Check that the domain name resolution is correct. For more details, see the logs.
141011	TTS_CLOUD_URL_INVALID	The URL is invalid.	The URL is invalid. Ping the URL and port to confirm they are reachable. Check the logs for details to locate the issue.
141012	TTS_CLOUD_PROTOCOL_ERROR	Cloud protocol error.	Cloud protocol error. Check the logs for details.
141013	TTS_CLOUD_PARAMETERS_ERROR	Parameter error.	Cloud parameter error. Check the log for details.
141014	TTS_CLOUD_UNKNOWN_WS_HEAD_TYPE	WebSocket uses an unknown header type.	This is a known issue with older clients. Upgrade to the latest version.

Server-side status codes

Status code	Status message	Cause	Solution
144001	TTS_CLOUD_AUTH_FAILED	Identity authentication failed.	Check whether the token used is correct and whether it has expired.
144002	TTS_CLOUD_INVALID_MESSAGE	Invalid message.	Check whether the sent message meets the requirements.
144003	TTS_CLOUD_INVALID_TOKEN	The token has expired or the parameter is invalid.	First, check whether the token used has expired. Then, check whether the parameter value is set reasonably.
144004	TTS_CLOUD_WAIT_TIMEOUT	Idle timeout.	Confirm whether data has not been sent to the server for a long time (more than 10 seconds).
144005	TTS_CLOUD_EXCEED_CONCURRENCY	Too many requests.	Check whether the number of concurrent connections or requests per second has been exceeded. If the concurrency limit is exceeded, upgrade from the Free Edition to the commercial version, or scale out the concurrency resources for the commercial version.
144006	TTS_CLOUD_DEFAULT_ERROR	Uncategorized error returned by the cloud.	For example, an invalid model ID was used. Check the log for details.
144100	TTS_CLOUD_INVALID_INTERFACE	The interface is not supported.	An unsupported operation was used.
144101	TTS_CLOUD_UNSUPPORTED_ORDER	Unsupported instruction.	An unsupported instruction was used.
144102	TTS_CLOUD_INVALID_ORDER	Invalid instruction.	The instruction format is incorrect.
144103	TTS_CLOUD_CLIENT_DISCONNECT	The client disconnected prematurely.	Check whether the connection was closed before the request was completed normally.
144200	TTS_CLOUD_INVALID_APPKEY	The application does not exist.	Check whether the application AppKey is correct and whether it belongs to the same account as the Token.
144300	TTS_CLOUD_INVALID_PARAM	Parameter error.	Check whether the correct parameters were passed.
144301	TTS_CLOUD_UNSENDAUDIO	The client did not send a command for 10 seconds.	Check for network issues, or check whether there are situations in your business where no data is sent.
144302	TTS_CLOUD_SENDAUDIO_TOO_FAST	The client is sending data too fast, and server resources are exhausted.	Check whether the client is sending packets too fast and whether they are sent at a 1:1 real-time rate.
144303	TTS_CLOUD_INVALID_AUDIO_FORMAT	The audio format sent by the client is incorrect.	Convert the audio data format to a format currently supported by the SDK.
144304	TTS_CLOUD_INVALID_INVOKE	The client method call is abnormal.	The client should call the send request operation first, and then call other operations after the request is sent.
144305	TTS_CLOUD_INVALID_MAX_SILENCE	The client's MAXSILENCE_PARAM method setting is abnormal.	The range of the MAXSILENCE_PARAM parameter is 200 to 2000.
144306	TTS_CLOUD_MISMATCHED_SAMPLERATE	The sample rate does not match.	Check whether the sample rate set during the call is consistent with the sample rate of the ASR model bound to the Appkey on the management console.
144400	TTS_CLOUD_SERVER_ERROR	TTS server error.	This can be ignored if it occurs randomly.
144401	TTS_CLOUD_INTERNAL_SERVER_ERROR	Server internal error.	Unknown error.
144402	TTS_CLOUD_SPEECH_TRANSCRIBER_SERVER_ERROR	The real-time speech recognition service is unavailable.	Check whether the real-time speech recognition service has a task backlog that is causing task submission to fail.
144403	TTS_CLOUD_SPEECH_TRANSCRIBER_REQUEST_TIMEOUT	The request to the real-time speech recognition service timed out.	Check the real-time speech recognition logs.
144404	TTS_CLOUD_INVOKE_SPEECH_TRANSCRIBER_FAILED	Failed to call the real-time speech recognition service.	Check whether the real-time speech recognition service is started and whether the port is open normally.
144405	TTS_CLOUD_SPEECH_TRANSCRIBER_BALANCE_FAILED	Real-time speech recognition service load balancing failed. Failed to get the IP address of the real-time speech recognition service.	Check for exceptions with the real-time speech recognition service machine in the VPC.
144406	TTS_CLOUD_SERVER_AGAIN	Internal call error.	Internal service error. The client needs to retry.