MaaS_Az_tts/Op_tts
Text To Speech Interface
Request URL
Request Parameters
| Parameter | Description | Example |
|---|---|---|
| model | Use Model | MaaS ASpeech |
| input | Text that needs to generate audio | how are you |
| voice | Available sounds when generating audio Optional values: "Alloy", "echo", "fable", "onyx", "nova", "shimmer" | alloy |
| response_format | Audio format Optional values: "mp3", "opus", "aac", "flac", "wav", "pcm" | mp3 |
| speed | Audio speed range is: 0.25 to 4.0. Supported by MaaS_Op_tts (Text To Speech) | 1 |
Response
File Stream
Request Example
Request
MaaS_Az_tts
curl --location --request POST ' https://genaiapi-m2.cloudsway.net/v1/ai/${ENDPOINT_PATH}/audio/speech' \
--header 'Authorization: Bearer ${your ak}' \
--header 'Content-Type: application/json' \
--header 'Connection: keep-alive' \
--data-raw '{
"input":"<speak version='\''1.0'\'' xml:lang='\''en-US'\''><voice xml:lang='\''en-US'\'' xml:gender='\''Female'\'' name='\''en-US-AvaMultilingualNeural'\''>吃葡萄不吐葡萄皮</voice></speak>",
"response_format":"audio-16khz-128kbitrate-mono-mp3"
}'
MaaS_Op_tts
curl 'http://genaiapi-m2.cloudsway.net/v1/audio/speech' \
-H 'Authorization: Bearer {Your_AK}' \
-H 'Content-Type: application/json' \
-d '{
"input":"hi,what is your name?",
"voice":"alloy",
"speed":1.0,
"response_format":"mp3"
}'
Response
file
Text To Speech HTTP Streaming Interface (MaaS_Az_tts only)
Request URL
Request Parameters
| Parameter | Description | Example |
|---|---|---|
| model | Use Model | MaaS ASpeech |
| input | Text (in SSML format) for which audio needs to be generated | \ |
| response_format | "mp3", "opus", "aac", "flac", "wav", "pcm" （Streaming）： amr-wb-16000hz audio-16khz-32kbitrate-mono-mp3 audio-16khz-64kbitrate-mono-mp3 audio-16khz-128kbitrate-mono-mp3 audio-24khz-48kbitrate-mono-mp3 audio-24khz-96kbitrate-mono-mp3 audio-24khz-160kbitrate-mono-mp3 audio-48khz-96kbitrate-mono-mp3 audio-48khz-192kbitrate-mono-mp3 g722-16khz-64kbps ogg-16khz-16bit-mono-opus ogg-24khz-16bit-mono-opus ogg-48khz-16bit-mono-opus raw-8khz-8bit-mono-alaw raw-8khz-8bit-mono-mulaw raw-8khz-16bit-mono-pcm raw-16khz-16bit-mono-pcm raw-16khz-16bit-mono-truesilk raw-22050hz-16bit-mono-pcm raw-24khz-16bit-mono-pcm raw-24khz-16bit-mono-truesilk raw-44100hz-16bit-mono-pcm raw-48khz-16bit-mono-pcm webm-16khz-16bit-mono-opus webm-24khz-16bit-24kbps-mono-opus webm-24khz-16bit-mono-opus 可选值（NonStreaming）： riff-8khz-8bit-mono-alaw riff-8khz-8bit-mono-mulaw riff-8khz-16bit-mono-pcm riff-22050hz-16bit-mono-pcm riff-24khz-16bit-mono-pcm riff-44100hz-16bit-mono-pcm riff-48khz-16bit-mono-pcm | audio-16khz-32kbitrate-mono-mp3 |
Request Example
curl --location --request POST 'http://genaiapi-m2.cloudsway.net/v1/ai/${ENDPOINT_PATH}/audio/speech/stream'
--header 'Authorization: Bearer ${your ak}' \
--header 'Content-Type: application/json' \
--header 'Accept: */*' \
--header 'Connection: keep-alive' \
--data-raw '{
"input":"<speak version='\''1.0'\'' xml:lang='\''en-US'\''><voice xml:lang='\''en-US'\'' xml:gender='\''Female'\'' name='\''en-US-AvaMultilingualNeural'\''>吃葡萄不吐葡萄皮</voice></speak>",
"response_format":"audio-16khz-32kbitrate-mono-mp3"
}'
Precautions
This HTTP request uses SSML to specify the voice and language. If the request body is too long, causing the generated audio to exceed 10 minutes, an error will be intercepted. It is recommended to split the text and resubmit the request.
Get the regional voice list of MaaS_Az_tts
Request URL
Request Parameters
None
Response
| Parameter | Description | Example |
|---|---|---|
| Name | Full name of voice | Microsoft Server Speech Text to Speech Voice (af-ZA, AdriNeural) |
| DisplayName | Display Name | Adri |
| LocalName | Local Name | Adri |
| ShortName | Abbreviation | af-ZA-AdriNeural |
| Gender | Voice Gender | Female |
| Locale | Language Environment | af-ZA |
| LocaleName | Locale Name | Afrikaans (South Africa) |
| SampleRateHertz | Sampling Hertz | 48000 |
| VoiceType | Voice Type | Neural |
| Status | Status | GA |
| WordsPerMinute | Words read per minute | 147 |
Request Example
Request
curl --location --request GET 'http://genaiapi-m2.cloudsway.net/v1/ai/${ENDPOINT_PATH}/cognitiveservices/voices/list' \
--header 'Authorization: Bearer ${your ak}' \
--header 'Content-Type: application/json' \
--header 'Connection: keep-alive' \
--data-raw ''
Response
[
{
"Name": "Microsoft Server Speech Text to Speech Voice (af-ZA, AdriNeural)",
"DisplayName": "Adri",
"LocalName": "Adri",
"ShortName": "af-ZA-AdriNeural",
"Gender": "Female",
"Locale": "af-ZA",
"LocaleName": "Afrikaans (South Africa)",
"SampleRateHertz": "48000",
"VoiceType": "Neural",
"Status": "GA",
"VoiceTag": {
"ModelSeries": [
"Monolingual"
],
"Source": [
"Azure"
],
"TailoredScenarios": [
"Assistant",
"Narration"
],
"VoicePersonalities": [
"Well-Rounded",
"Animated",
"Bright"
]
},
"WordsPerMinute": "147"
},
......
]
Integrated Interface Call
Note that the parameters of the fusion interface are the same as those of the non-fusion interface, but the model field is required, and the model product code should be passed in.
Request URL
MaaS_Az_tts
Request Example
curl 'http://genaiapi-m2.cloudsway.net/v1/audio/speech' \
-H 'Authorization: Bearer {Your_AK}' \
-H 'Content-Type: application/json' \
-d '{
"input": "<speak version=\"1.0\" xml:lang=\"en-US\"><voice xml:lang=\"en-US\" xml:gender=\"Female\" name=\"en-US-AvaMultilingualNeural\">my voice is my passport verify me</voice></speak>",
"response_format": "audio-16khz-128kbitrate-mono-mp3",
"model": "MaaS_Az_tts"
}'
MaaS_Op_tts
Request Example