Domain name for API request: trtc.ai.intl.tencentcloudapi.com.
This API is used to stream text-to-speech.
A maximum of 20 requests can be initiated per second for this API.
The following request parameter list only provides API request parameters and some common parameters. For the complete common parameter list, see Common Request Parameters.
| Parameter Name | Required | Type | Description |
|---|---|---|---|
| Action | Yes | String | Common Params. The value used for this API: TextToSpeechSSE. |
| Version | Yes | String | Common Params. The value used for this API: 2019-07-22. |
| Region | Yes | String | Common Params. For more information, please see the list of regions supported by the product. This API only supports: ap-singapore. |
| Text | Yes | String | Text to be converted to speech. length range: [1, 255]. |
| Voice | Yes | Voice | Audio configuration for text-to-speech. |
| SdkAppId | Yes | Integer | Specifies the SdkAppId of TRTC. |
| AudioFormat | No | AudioFormat | Specifies the output audio format for text-to-speech. |
| Model | No | String | TTS model, current fixed value: flow_01_turbo. |
| Language | No | String | Language to be synthesised (ISO 639-1). supports zh (chinese), en (english), yue (cantonese), ja (japanese), and ko (korean). defaults to auto-identification. |
| PronunciationDict.N | No | Array of PronunciationDict | |
| AlignmentMode | No | Integer |
| Parameter Name | Type | Description |
|---|---|---|
| RequestId | String | The unique request ID, generated by the server, will be returned for every request (if the request fails to reach the server for other reasons, the request will not obtain a RequestId). RequestId is required for locating a problem. As a streaming response API, when the request is successfully completed, the RequestId will be placed in the Header "X-TC-RequestId" of the HTTP response. |
If an error occurs during the synthesis process, it will be returned in SSE format.
POST / HTTP/1.1
Host: trtc.ai.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: TextToSpeechSSE
<Common Request Parameters>
{
"Text": "hello",
"SdkAppId": 14600000000,
"Voice": {
"VoiceId": "v-female-R2s4N9qJ"
},
"AlignmentMode": 1
}
data: {"Type": "chunk", "RequestId": "456e7890-e12b-34d5-a678-426614174000", "ChunkId": "chunk_0", "Audio": "base64_audio...", "Seq": 0, "IsEnd": false}
data: {"Type": "error", "RequestId": "456e7890-e12b-34d5-a678-426614174000", "Error": {"Code": "InternalError", "Message": "internal error message"}}
If a parameter error occurs before the formal synthesis begins, a JSON error will be returned immediately. You can detect this situation by checking the Content-Type
POST / HTTP/1.1
Host: trtc.ai.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: TextToSpeechSSE
<Common Request Parameters>
{
"Text": "hello",
"SdkAppId": 14600000000,
"Voice": {
"VoiceId": "fake"
},
"AlignmentMode": 1
}
{
"Response": {
"RequestId": "78033210-b9c2-4c2a-b378-6a0c63646d81",
"Error": {
"Code": "InvalidParameter.VoiceId",
"Message": "Cloud API TTS parameter error: Voice ID 'fake' not found. Please check if the voice exists or create it via voice clone API."
}
}
}
The SSE interface must use the trtc.ai.tencentcloudapi.com domain, otherwise, the API call will fail.
POST / HTTP/1.1
Host: trtc.ai.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: TextToSpeechSSE
<Common Request Parameters>
{
"Text": "hello",
"SdkAppId": 14600000000,
"Voice": {
"VoiceId": "v-female-R2s4N9qJ"
},
"AlignmentMode": 1
}
data: {"Type": "chunk", "RequestId": "456e7890-e12b-34d5-a678-426614174000", "ChunkId": "chunk_0", "Audio": "base64_audio...", "Seq": 0, "IsEnd": false}
data: {"Type": "chunk", "RequestId": "456e7890-e12b-34d5-a678-426614174000", "ChunkId": "chunk_1", "Audio": "base64_audio...", "Seq": 1, "Alignments": [{"TimeBeginMs": 0, "TimeEndMs": 600, "TextBegin": 0, "TextEnd": 2}, "IsEnd": false}
data: {"Type": "chunk", "RequestId": "456e7890-e12b-34d5-a678-426614174000", "ChunkId": "chunk_2", "Audio": "base64_audio...", "Seq": 2, "IsEnd": true}
TencentCloud API 3.0 integrates SDKs that support various programming languages to make it easier for you to call APIs.
The following only lists the error codes related to the API business logic. For other error codes, see Common Error Codes.
| Error Code | Description |
|---|---|
| InvalidParameter.Pitch | Invalid tone. |
| InvalidParameter.PronunciationDict | |
| InvalidParameter.SampleRate | Invalid sampling rate. |
| InvalidParameter.Speed | Invalid speed of sound. |
| InvalidParameter.TextLength | Invalid text length. |
| InvalidParameter.VoiceId | Invalid VoiceId. |
| InvalidParameter.Volume | Invalid volume. |
| MissingParameter.APIKey | Invalid api key. |
| UnsupportedOperation.InternalError | Unsupported operation. |
| UnsupportedOperation.NotAllowed | Not allowed to use. contact technical personnel. |
피드백