Skip to content

Commit 4a40eac

Browse files
eric-urbaneric-urban
committed
february tts release notes
1 parent 7e48c10 commit 4a40eac

File tree

2 files changed

+96
-5
lines changed

2 files changed

+96
-5
lines changed

‎articles/ai-services/speech-service/embedded-speech.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -280,7 +280,7 @@ For cloud speech, you use the `SpeechConfig` object, as shown in the [speech to
280280

281281
## Embedded voices capabilities
282282

283-
For embedded voices, it's essential to note that certain SSML tags might not be currently supported due to differences in the model structure. For detailed information regarding the unsupported SSML tags, refer to the following table.
283+
For embedded voices, it's essential to note that certain [Speech synthesis markup language (SSML)](./speech-synthesis-markup.md) tags might not be currently supported due to differences in the model structure. For detailed information regarding the unsupported SSML tags, refer to the following table.
284284

285285
| Level 1 | Level 2 | Sub values | Support in embedded NTTS |
286286
|---------|---------|---------|---------|
@@ -299,7 +299,7 @@ For embedded voices, it's essential to note that certain SSML tags might not be
299299
| | volume | | No |
300300
| | fadein | | No |
301301
| | fadeout | | No |
302-
| msttsexpress-as | style | | No |
302+
| msttsexpress-as | style | | Yes<sup>1</sup> |
303303
| | styledegree | | No |
304304
| | role | | No |
305305
| msttssilence | | | No |
@@ -320,6 +320,8 @@ For embedded voices, it's essential to note that certain SSML tags might not be
320320
| speak | | | Yes |
321321
| voice | | | No |
322322

323+
<sup>1</sup> The [`msttsexpress-as`](./speech-synthesis-markup-voice.md#use-speaking-styles-and-roles) style is supported only for the `en-US-JennyNeural` voice.
324+
323325
## Related content
324326

325327
- [Read about text to speech on devices for disconnected and hybrid scenarios](https://techcommunity.microsoft.com/t5/ai-cognitive-services-blog/azure-neural-tts-now-available-on-devices-for-disconnected-and/ba-p/3716797)

‎articles/ai-services/speech-service/includes/release-notes/release-notes-tts.md

Lines changed: 92 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -2,22 +2,111 @@
22
author: eric-urban
33
ms.service: azure-ai-speech
44
ms.topic: include
5-
ms.date: 1/13/2025
5+
ms.date: 2/18/2025
66
ms.author: eur
77
ms.custom: references_regions
88
---
99

10+
### February 2025 release
11+
12+
#### Version 1.1 of HD voices (Public preview)
13+
14+
Updated 13 current HD voices to the version 1.1 (latest) to support multilingual voices.
15+
16+
- Specifying the "latest" model defaults to v1.1
17+
- v1.1 supports multilingual
18+
- If you want to call older version, specify the version in the voice name:
19+
- Version 1.0: `en-US-Ava:DragonHDV1.0Neural`
20+
- Latest (currently V1.1): `en-US-Ava:DragonHDLatestNeural`
21+
22+
| **Locale (BCP-47)** | **Voice name** |
23+
|---------------------|---------------------------|
24+
| `de-DE` | `de-DE-Seraphina:DragonHDLatestNeural` (Female) |
25+
| `en-US` | `en-US-Brian:DragonHDLatestNeural` (Male) |
26+
| `en-US` | `en-US-Davis:DragonHDLatestNeural` (Male) |
27+
| `en-US` | `en-US-Ava:DragonHDLatestNeural` (Female) |
28+
| `en-US` | `en-US-Andrew:DragonHDLatestNeural` (Male) |
29+
| `en-US` | `en-US-Andrew2:DragonHDLatestNeural` (Male) - optimized for free-talking |
30+
| `en-US` | `en-US-Emma:DragonHDLatestNeural` (Female) |
31+
| `en-US` | `en-US-Emma2:DragonHDLatestNeural` (Female) - optimized for free-talking |
32+
| `en-US` | `en-US-Steffan:DragonHDLatestNeural` (Male) |
33+
| `en-US` | `en-US-Aria:DragonHDLatestNeural` (Female) |
34+
| `en-US` | `en-US-Jenny:DragonHDLatestNeural` (Female) |
35+
| `ja-JP` | `ja-JP-Masaru:DragonHDLatestNeural` (Male) |
36+
| `zh-CN` | `zh-CN-Xiaochen:DragonHDLatestNeural` (Female) |
37+
38+
#### Public preview of new HD voices
39+
40+
Added 14 more HD voices that are only available in version 1.1.
41+
42+
| **Locale (BCP-47)** | **Voice name** |
43+
|---------------------|---------------------------|
44+
| `de-DE` | `de-DE-Florian:DragonHDLatestNeural` (Male) |
45+
| `en-US` | `en-US-Adam:DragonHDLatestNeural` (Male) |
46+
| `en-US` | `en-US-Brain:DragonHDLatestNeural` (Male) |
47+
| `en-US` | `en-US-Davis:DragonHDLatestNeural` (Male) |
48+
| `en-US` | `en-US-Phoebe:DragonHDLatestNeural` (Female) |
49+
| `en-US` | `en-US-Serena:DragonHDLatestNeural` (Female) |
50+
| `en-US` | `en-US-Alloy:DragonHDLatestNeural` (Male) |
51+
| `en-US` | `en-US-Nova:DragonHDLatestNeural` (Female) |
52+
| `es-ES` | `es-ES-Ximena:DragonHDLatestNeural` (Female) |
53+
| `es-ES` | `es-ES-Tristan:DragonHDLatestNeural` (Male) |
54+
| `fr-FR` | `fr-FR-Vivienne:DragonHDLatestNeural` (Female) |
55+
| `fr-FR` | `fr-FR-Remy:DragonHDLatestNeural` (Male) |
56+
| `ja-JP` | `ja-JP-Nanami:DragonHDLatestNeural` (Female) |
57+
| `zh-CN` | `zh-CN-Yunfan:DragonHDLatestNeural` (Male) |
58+
59+
#### Azure OpenAI Service turbo voices
60+
61+
These turbo voices are now generally available:
62+
63+
| **Locale (BCP-47)** | **Voice name** |
64+
|---------------------|---------------------------|
65+
| `en-US` | `en-US-AlloyTurboMultilingualNeural` (Male) |
66+
| `en-US` | `en-US-EchoTurboMultilingualNeural` (Male) |
67+
| `en-US` | `en-US-FableTurboMultilingualNeural` (Neutral) |
68+
| `en-US` | `en-US-NovaTurboMultilingualNeural` (Female) |
69+
| `en-US` | `en-US-OnyxTurboMultilingualNeural` (Male) |
70+
| `en-US` | `en-US-ShimmerTurboMultilingualNeural` (Female) |
71+
72+
#### Voice quality improvements
73+
74+
Improved the quality of 16 voices.
75+
76+
| **Locale (BCP-47)** | **Voice name** |
77+
|---------------------|---------------------------|
78+
| `ar-EG` | `ar-EG-ShakirNeural` (Male) |
79+
| `ca-ES` | `ca-ES-EnricNeural` (Male) |
80+
| `en-IE` | `en-IE-EmilyNeural` (Female) |
81+
| `fi-FI` | `fi-FI-HarriNeural` (Male) |
82+
| `fi-FI` | `fi-FI-SelmaNeural` (Female) |
83+
| `fr-CH` | `fr-CH-FabriceNeural` (Female) |
84+
| `hr-HR` | `hr-HR-GabrijelaNeural` (Female) |
85+
| `nl-NL` | `nl-NL-MaartenNeural` (Male) |
86+
| `pt-PT` | `pt-PT-RaquelNeural` (Female) |
87+
| `ro-RO` | `ro-RO-AlinaNeural` (Female) |
88+
| `sv-SE` | `sv-SE-MattiasNeural` (Male) |
89+
| `sv-SE` | `sv-SE-SofieNeural` (Female) |
90+
| `vi-VN` | `vi-VN-HoaiMyNeural` (Female) |
91+
| `vi-VN` | `vi-VN-NamMinhNeural` (Male) |
92+
| `zh-HK` | `zh-HK-HiuMaanNeural` (Female) |
93+
| `zh-HK` | `zh-HK-WanLungNeural` (Male) |
94+
95+
#### GA - Multi-style embedded Jenny
96+
97+
Added style support for `en-US-JennyNeural` in [embedded speech](../../embedded-speech.md). The same styles are supported as in the cloud. The following styles are supported: `angry`, `assistant`, `chat`, `cheerful`, `customerservice`, `excited`, `friendly`, `hopeful`, `newscast`, `sad`, `shouting`, `terrified`, `unfriendly`, and `whispering`.
98+
1099
### January 2025 release
11100

12-
##### Custom avatar training
101+
#### Custom avatar training
13102

14103
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.
15104

16105
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).
17106

18107
### October 2024 release
19108

20-
##### Prebuilt neural voice
109+
#### Prebuilt neural voice
21110

22111
Introduced 4 turbo version of Azure OpenAI voices in public preview: `en-US-EchoTurboMultilingualNeural`, `en-US-FableTurboMultilingualNeural`, `en-US-OnyxTurboMultilingualNeural`, and `en-US-ShimmerTurboMultilingualNeural`. Turbo version of Azure OpenAI voices has the similar voice persona as Azure OpenAI voices but supports extra features. Turbo voices support the full set of SSML elements and more features like word boundary, just like other Azure AI Speech voices. See the [full language and voice list](../../language-support.md?tabs=tts) for more information.
23112

0 commit comments

Comments
 (0)