Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,516 questions
Can some voices on spx text to speech not read phonetic alphabet ?
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(268.8, 8%, 36%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EH%3C/text%3E%3C/svg%3E)
Houda
0
Reputation points
Hello ! I am using the Azure text to speech service with SSML to read phonetic alphabet, it works well except for when I pick the voice "Andrew multilingual". The spx command does not generate any voice but there is no error in the output. Are some voices not supported by the SSML phonetic alphabet feature ? If so how do I know which ones, considering there's no error message that tells me that that's the issue ? Thank you in advance !
{count} votes
-
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(195.2, 4%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EVM%3C/text%3E%3C/svg%3E)
VasaviLankipalle-MSFT 15,836 Reputation points2024-06-10T22:27:01.79+00:00 Hello @Houda , Thanks for using Microsoft Q&A Platform.
Is it possible to share detailed information regarding the locale and the sample data to reproduce the same on our end?
-
Houda 0 Reputation points
2024-06-11T07:46:25.09+00:00 The region I'm using is "francecentral" and as for the command I tried it's this :
spx synthesize --ssml "<speak xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='https://www.w3.org/2001/mstts' xml:lang='en-US' version='1.0'><voice name='en-US-AndrewMultilingualNeural'><phoneme ph='ðɪs ɪz maɪ tɛkst tuː tɛst' alphabet='ipa'/></voice></speak>" --speakers
The same command works when I use a different voice. Also the voice 'en-US-AndrewMultilingualNeural' works without the phoneme element.
-
Houda 0 Reputation points
2024-06-11T07:49:56.8933333+00:00 The region I'm using is "francecentral" and as for the command I tried it's this :
spx synthesize --ssml "<speak xmlns='http://www.w3.org/2001/10/synthesis' xmlns:mstts='https://www.w3.org/2001/mstts' xml:lang='en-US' version='1.0'><voice name='en-US-AndrewMultilingualNeural'><phoneme ph='ðɪs ɪz maɪ tɛkst tuː tɛst' alphabet='ipa'/></voice></speak>" --speakers
The same command works when I use a different voice. Also the voice 'en-US-AndrewMultilingualNeural' works without the phoneme element.
Sign in to comment