You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/speech-service/includes/release-notes/release-notes-tts.md
+9-1Lines changed: 9 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -2,11 +2,19 @@
2
2
author: eric-urban
3
3
ms.service: azure-ai-speech
4
4
ms.topic: include
5
-
ms.date: 11/11/2024
5
+
ms.date: 1/13/2025
6
6
ms.author: eur
7
7
ms.custom: references_regions
8
8
---
9
9
10
+
### January 2025 release
11
+
P
12
+
##### Custom avatar training
13
+
14
+
You can now train custom avatars in [Speech Studio](https://speech.microsoft.com/portal/talkingavatar). Previously, you had to wait for Microsoft to train your custom avatar.
15
+
16
+
For more details about how to create a custom avatar, see [create a custom text to speech avatar](../../text-to-speech-avatar/custom-avatar-create.md).
@@ -27,48 +27,267 @@ Keep in mind the following points:
27
27
28
28
## Regions
29
29
30
-
The regions in this table support most of the core features of the Speech service, such as speech to text, text to speech, pronunciation assessment, and translation. Some features, such as fast transcription and batch synthesis API, require specific regions. For the features that require specific regions, the table indicates the regions that support them.
31
-
32
-
|**Region**|**Fast transcription**|**Batch synthesis API**|**Custom speech**|**Custom speech training with audio**<sup>1</sup> |**Custom neural voice**|**Custom neural voice training**<sup>2</sup> |**Custom neural voice high performance endpoint**|**Personal voice**|**Text to speech avatar**|**Video translation**|**Custom keyword advanced models**|**Keyword verification**|**Speaker recognition**|**Intent recognition**<sup>3</sup> |**Voice assistants**<sup>3</sup> |
The regions in these tables support most of the core features of the Speech service, such as speech to text, text to speech, pronunciation assessment, and translation. Some features, such as fast transcription and batch synthesis API, require specific regions. For the features that require specific regions, the table indicates the regions that support them.
31
+
32
+
# [Geographies](#tab/geographies)
33
+
34
+
| Geography | Region | Region identifier |
35
+
| ----- | ------- | ------ |
36
+
| Africa | South Africa North |`southafricanorth`|
37
+
| Asia Pacific | East Asia |`eastasia`|
38
+
| Asia Pacific | Southeast Asia |`southeastasia`|
39
+
| Asia Pacific | Australia East |`australiaeast`|
40
+
| Asia Pacific | Central India |`centralindia`|
41
+
| Asia Pacific | Japan East |`japaneast`|
42
+
| Asia Pacific | Japan West |`japanwest`|
43
+
| Asia Pacific | Korea Central |`koreacentral`|
44
+
| Canada | Canada Central |`canadacentral`|
45
+
| Europe | North Europe |`northeurope`|
46
+
| Europe | West Europe |`westeurope`|
47
+
| Europe | France Central |`francecentral`|
48
+
| Europe | Germany West Central |`germanywestcentral`|
49
+
| Europe | Norway East |`norwayeast`|
50
+
| Europe | Sweden Central |`swedencentral`|
51
+
| Europe | Switzerland North |`switzerlandnorth`|
52
+
| Europe | Switzerland West |`switzerlandwest`|
53
+
| Europe | UK South |`uksouth`|
54
+
| Middle East | UAE North |`uaenorth`|
55
+
| South America | Brazil South |`brazilsouth`|
56
+
| Qatar | Qatar Central |`qatarcentral`|
57
+
| US | Central US |`centralus`|
58
+
| US | East US |`eastus`|
59
+
| US | East US 2 |`eastus2`|
60
+
| US | North Central US |`northcentralus`|
61
+
| US | South Central US |`southcentralus`|
62
+
| US | West Central US |`westcentralus`|
63
+
| US | West US |`westus`|
64
+
| US | West US 2 |`westus2`|
65
+
| US | West US 3 |`westus3`|
66
+
67
+
68
+
# [Speech to text](#tab/stt)
69
+
70
+
|**Region**|**Fast transcription**|**Custom speech**|**Custom speech training with audio**<sup>1</sup> |
71
+
|-----|-----|-----|-----|
72
+
| australiaeast | ✅ | ✅ | ✅ |
73
+
| brazilsouth | ✅ | ✅ ||
74
+
| canadacentral || ✅ | ✅ |
75
+
| centralindia | ✅ | ✅ | ✅ |
76
+
| centralus || ✅ ||
77
+
| eastasia || ✅ ||
78
+
| eastus | ✅ | ✅ | ✅ |
79
+
| eastus2 | ✅ | ✅ | ✅ |
80
+
| francecentral | ✅ | ✅ ||
81
+
| germanywestcentral || ✅ ||
82
+
| japaneast | ✅ | ✅ ||
83
+
| japanwest || ✅ ||
84
+
| koreacentral || ✅ ||
85
+
| northcentralus | ✅ | ✅ ||
86
+
| northeurope | ✅ | ✅ | ✅ |
87
+
| norwayeast || ✅ ||
88
+
| qatarcentral || ✅ ||
89
+
| southafricanorth || ✅ ||
90
+
| southcentralus | ✅ | ✅ | ✅ |
91
+
| southeastasia | ✅ | ✅ | ✅ |
92
+
| swedencentral | ✅ | ✅ ||
93
+
| switzerlandnorth || ✅ ||
94
+
| switzerlandwest || ✅ ||
95
+
| uaenorth || ✅ ||
96
+
| uksouth || ✅ | ✅ |
97
+
| westcentralus || ✅ ||
98
+
| westeurope | ✅ | ✅ | ✅ |
99
+
| westus | ✅ | ✅ ||
100
+
| westus2 | ✅ | ✅ | ✅ |
101
+
| westus3 | ✅ | ✅ ||
64
102
65
103
<sup>1</sup> The region has dedicated hardware for custom speech training. If you plan to train a custom model with audio data, you must use one of the regions with dedicated hardware. Then you can [copy the trained model](how-to-custom-speech-train-model.md#copy-a-model) to another region.
66
104
67
-
<sup>2</sup> The region is available for custom neural voice training. You can copy a trained neural voice model to other regions for deployment.
105
+
# [Text to speech](#tab/tts)
106
+
107
+
|**Region**|**Neural text to speech**|**Batch synthesis API**|**HD voices**|**Azure OpenAI voices**|**Custom neural voice**|**Custom neural voice training**|**Custom neural voice high performance endpoint**|**Personal voice**|**Text to speech avatar**|**Custom avatar**|**Custom avatar training**|
<sup>3</sup> The [Speech SDK](speech-sdk.md) supports intent recognition and voice assistant capabilities through [Direct Line Speech](./direct-line-speech.md).
140
+
# [Speech translation](#tab/speech-translation)
141
+
142
+
|**Region**|**Video translation**|
143
+
|-----|-----|
144
+
| australiaeast ||
145
+
| brazilsouth ||
146
+
| canadacentral ||
147
+
| centralindia ||
148
+
| centralus ||
149
+
| eastasia ||
150
+
| eastus | ✅ |
151
+
| eastus2 ||
152
+
| francecentral ||
153
+
| germanywestcentral ||
154
+
| japaneast ||
155
+
| japanwest ||
156
+
| koreacentral ||
157
+
| northcentralus ||
158
+
| northeurope ||
159
+
| norwayeast ||
160
+
| qatarcentral ||
161
+
| southafricanorth ||
162
+
| southcentralus ||
163
+
| southeastasia ||
164
+
| swedencentral ||
165
+
| switzerlandnorth ||
166
+
| switzerlandwest ||
167
+
| uaenorth ||
168
+
| uksouth ||
169
+
| westcentralus ||
170
+
| westeurope ||
171
+
| westus ||
172
+
| westus2 ||
173
+
| westus3 ||
174
+
175
+
# [Intent recognition](#tab/intent-recognition)
176
+
177
+
|**Region**|**Intent recognition**|
178
+
|-----|-----|
179
+
| australiaeast | ✅ |
180
+
| brazilsouth | ✅ |
181
+
| canadacentral ||
182
+
| centralindia ||
183
+
| centralus ||
184
+
| eastasia | ✅ |
185
+
| eastus | ✅ |
186
+
| eastus2 | ✅ |
187
+
| francecentral ||
188
+
| germanywestcentral ||
189
+
| japaneast ||
190
+
| japanwest ||
191
+
| koreacentral ||
192
+
| northcentralus ||
193
+
| northeurope | ✅ |
194
+
| norwayeast ||
195
+
| qatarcentral ||
196
+
| southafricanorth ||
197
+
| southcentralus | ✅ |
198
+
| southeastasia | ✅ |
199
+
| swedencentral ||
200
+
| switzerlandnorth ||
201
+
| switzerlandwest ||
202
+
| uaenorth ||
203
+
| uksouth ||
204
+
| westcentralus | ✅ |
205
+
| westeurope | ✅ |
206
+
| westus | ✅ |
207
+
| westus2 | ✅ |
208
+
| westus3 ||
209
+
210
+
> [!NOTE]
211
+
> The [Speech SDK](speech-sdk.md) supports intent recognition through [Direct Line Speech](./direct-line-speech.md).
0 commit comments