livekit-plugins-google 1.2.3__tar.gz → 1.2.5__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of livekit-plugins-google might be problematic. Click here for more details.

Files changed (19) hide show
  1. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/PKG-INFO +2 -2
  2. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/models.py +123 -30
  3. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/stt.py +6 -2
  4. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/version.py +1 -1
  5. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/pyproject.toml +1 -1
  6. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/.gitignore +0 -0
  7. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/README.md +0 -0
  8. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/__init__.py +0 -0
  9. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/beta/__init__.py +0 -0
  10. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/beta/gemini_tts.py +0 -0
  11. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/beta/realtime/__init__.py +0 -0
  12. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/beta/realtime/api_proto.py +0 -0
  13. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/beta/realtime/realtime_api.py +0 -0
  14. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/llm.py +0 -0
  15. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/log.py +0 -0
  16. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/py.typed +0 -0
  17. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/tools.py +0 -0
  18. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/tts.py +0 -0
  19. {livekit_plugins_google-1.2.3 → livekit_plugins_google-1.2.5}/livekit/plugins/google/utils.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: livekit-plugins-google
3
- Version: 1.2.3
3
+ Version: 1.2.5
4
4
  Summary: Agent Framework plugin for services from Google Cloud
5
5
  Project-URL: Documentation, https://docs.livekit.io
6
6
  Project-URL: Website, https://livekit.io/
@@ -22,7 +22,7 @@ Requires-Dist: google-auth<3,>=2
22
22
  Requires-Dist: google-cloud-speech<3,>=2
23
23
  Requires-Dist: google-cloud-texttospeech<3,>=2.27
24
24
  Requires-Dist: google-genai>=v1.23.0
25
- Requires-Dist: livekit-agents>=1.2.3
25
+ Requires-Dist: livekit-agents>=1.2.5
26
26
  Description-Content-Type: text/markdown
27
27
 
28
28
  # Google AI plugin for LiveKit Agents
@@ -15,81 +15,174 @@ SpeechModels = Literal[
15
15
  ]
16
16
 
17
17
  SpeechLanguages = Literal[
18
- "en-US",
19
- "ja-JP",
20
- "en-IN",
21
- "en-GB",
22
- "hi-IN",
23
18
  "af-ZA",
24
- "sq-AL",
25
19
  "am-ET",
20
+ "ar-AE",
21
+ "ar-BH",
22
+ "ar-DZ",
26
23
  "ar-EG",
27
- "hy-AM",
24
+ "ar-IL",
25
+ "ar-IQ",
26
+ "ar-JO",
27
+ "ar-KW",
28
+ "ar-LB",
29
+ "ar-MA",
30
+ "ar-MR",
31
+ "ar-OM",
32
+ "ar-PS",
33
+ "ar-QA",
34
+ "ar-SA",
35
+ "ar-TN",
36
+ "ar-YE",
37
+ "as-IN",
28
38
  "ast-ES",
29
39
  "az-AZ",
30
- "eu-ES",
31
40
  "be-BY",
32
- "bs-BA",
33
41
  "bg-BG",
34
- "my-MM",
42
+ "bn-BD",
43
+ "bn-IN",
44
+ "bs-BA",
35
45
  "ca-ES",
36
46
  "ceb-PH",
37
47
  "ckb-IQ",
38
- "zh-Hans-CN",
39
- "yue-Hant-HK",
40
- "zh-TW",
41
- "hr-HR",
48
+ "cmn-Hans-CN",
49
+ "cmn-Hant-TW",
42
50
  "cs-CZ",
51
+ "cy-GB",
43
52
  "da-DK",
44
- "nl-NL",
53
+ "de-AT",
54
+ "de-CH",
55
+ "de-DE",
56
+ "el-GR",
45
57
  "en-AU",
58
+ "en-CA",
59
+ "en-GB",
60
+ "en-HK",
61
+ "en-IE",
62
+ "en-IN",
63
+ "en-NZ",
64
+ "en-PK",
65
+ "en-SG",
66
+ "en-US",
67
+ "es-419",
68
+ "es-AR",
69
+ "es-BO",
70
+ "es-CL",
71
+ "es-CO",
72
+ "es-CR",
73
+ "es-DO",
74
+ "es-EC",
75
+ "es-ES",
76
+ "es-GT",
77
+ "es-HN",
78
+ "es-MX",
79
+ "es-NI",
80
+ "es-PA",
81
+ "es-PE",
82
+ "es-PR",
83
+ "es-SV",
84
+ "es-US",
85
+ "es-UY",
86
+ "es-VE",
46
87
  "et-EE",
47
- "fil-PH",
88
+ "eu-ES",
89
+ "fa-IR",
90
+ "ff-SN",
48
91
  "fi-FI",
92
+ "fil-PH",
93
+ "fr-BE",
49
94
  "fr-CA",
95
+ "fr-CH",
50
96
  "fr-FR",
97
+ "ga-IE",
51
98
  "gl-ES",
52
- "ka-GE",
53
- "de-DE",
54
- "el-GR",
55
99
  "gu-IN",
56
100
  "ha-NG",
57
- "iw-IL",
58
101
  "hi-IN",
102
+ "hr-HR",
59
103
  "hu-HU",
60
- "is-IS",
104
+ "hy-AM",
61
105
  "id-ID",
106
+ "ig-NG",
107
+ "is-IS",
108
+ "it-CH",
62
109
  "it-IT",
110
+ "iw-IL",
63
111
  "ja-JP",
64
112
  "jv-ID",
65
- "kea-CV",
113
+ "ka-GE",
66
114
  "kam-KE",
67
- "kn-IN",
115
+ "kea-CV",
68
116
  "kk-KZ",
69
117
  "km-KH",
118
+ "kn-IN",
70
119
  "ko-KR",
71
120
  "ky-KG",
72
- "lo-LA",
73
- "lv-LV",
121
+ "lb-LU",
122
+ "lg-UG",
74
123
  "ln-CD",
124
+ "lo-LA",
75
125
  "lt-LT",
76
126
  "luo-KE",
77
- "lb-LU",
127
+ "lv-LV",
128
+ "mi-NZ",
78
129
  "mk-MK",
130
+ "ml-IN",
131
+ "mn-MN",
132
+ "mr-IN",
133
+ "ms-MY",
134
+ "mt-MT",
135
+ "my-MM",
136
+ "ne-NP",
137
+ "nl-BE",
138
+ "nl-NL",
79
139
  "no-NO",
140
+ "nso-ZA",
141
+ "ny-MW",
142
+ "oc-FR",
143
+ "om-ET",
144
+ "or-IN",
145
+ "pa-Guru-IN",
80
146
  "pl-PL",
147
+ "ps-AF",
81
148
  "pt-BR",
82
149
  "pt-PT",
83
150
  "ro-RO",
84
151
  "ru-RU",
85
- "es-CO",
86
- "es-MX",
87
- "es-US",
152
+ "rup-BG",
153
+ "rw-RW",
154
+ "sd-IN",
155
+ "si-LK",
156
+ "sk-SK",
157
+ "sl-SI",
158
+ "sn-ZW",
159
+ "so-SO",
160
+ "sq-AL",
161
+ "sr-RS",
162
+ "ss-Latn-ZA",
163
+ "st-ZA",
164
+ "su-ID",
165
+ "sv-SE",
166
+ "sw",
167
+ "sw-KE",
168
+ "ta-IN",
169
+ "te-IN",
170
+ "tg-TJ",
88
171
  "th-TH",
172
+ "tn-Latn-ZA",
89
173
  "tr-TR",
174
+ "ts-ZA",
90
175
  "uk-UA",
176
+ "umb-AO",
177
+ "ur-PK",
178
+ "uz-UZ",
179
+ "ve-ZA",
91
180
  "vi-VN",
92
- "da-DK",
181
+ "wo-SN",
182
+ "xh-ZA",
183
+ "yo-NG",
184
+ "yue-Hant-HK",
185
+ "zu-ZA",
93
186
  ]
94
187
 
95
188
  Gender = Literal["male", "female", "neutral"]
@@ -66,6 +66,7 @@ class STTOptions:
66
66
  interim_results: bool
67
67
  punctuate: bool
68
68
  spoken_punctuation: bool
69
+ enable_word_time_offsets: bool
69
70
  model: SpeechModels | str
70
71
  sample_rate: int
71
72
  min_confidence_threshold: float
@@ -97,6 +98,7 @@ class STT(stt.STT):
97
98
  interim_results: bool = True,
98
99
  punctuate: bool = True,
99
100
  spoken_punctuation: bool = False,
101
+ enable_word_time_offsets: bool = True,
100
102
  model: SpeechModels | str = "latest_long",
101
103
  location: str = "global",
102
104
  sample_rate: int = 16000,
@@ -119,6 +121,7 @@ class STT(stt.STT):
119
121
  interim_results(bool): whether to return interim results (default: True)
120
122
  punctuate(bool): whether to punctuate the audio (default: True)
121
123
  spoken_punctuation(bool): whether to use spoken punctuation (default: False)
124
+ enable_word_time_offsets(bool): whether to enable word time offsets (default: True)
122
125
  model(SpeechModels): the model to use for recognition default: "latest_long"
123
126
  location(str): the location to use for recognition default: "global"
124
127
  sample_rate(int): the sample rate of the audio default: 16000
@@ -158,6 +161,7 @@ class STT(stt.STT):
158
161
  interim_results=interim_results,
159
162
  punctuate=punctuate,
160
163
  spoken_punctuation=spoken_punctuation,
164
+ enable_word_time_offsets=enable_word_time_offsets,
161
165
  model=model,
162
166
  sample_rate=sample_rate,
163
167
  min_confidence_threshold=min_confidence_threshold,
@@ -238,7 +242,7 @@ class STT(stt.STT):
238
242
  features=cloud_speech.RecognitionFeatures(
239
243
  enable_automatic_punctuation=config.punctuate,
240
244
  enable_spoken_punctuation=config.spoken_punctuation,
241
- enable_word_time_offsets=True,
245
+ enable_word_time_offsets=config.enable_word_time_offsets,
242
246
  ),
243
247
  model=config.model,
244
248
  language_codes=config.languages,
@@ -490,7 +494,7 @@ class SpeechStream(stt.SpeechStream):
490
494
  model=self._config.model,
491
495
  features=cloud_speech.RecognitionFeatures(
492
496
  enable_automatic_punctuation=self._config.punctuate,
493
- enable_word_time_offsets=True,
497
+ enable_word_time_offsets=self._config.enable_word_time_offsets,
494
498
  enable_spoken_punctuation=self._config.spoken_punctuation,
495
499
  ),
496
500
  ),
@@ -12,4 +12,4 @@
12
12
  # See the License for the specific language governing permissions and
13
13
  # limitations under the License.
14
14
 
15
- __version__ = "1.2.3"
15
+ __version__ = "1.2.5"
@@ -27,7 +27,7 @@ dependencies = [
27
27
  "google-cloud-speech >= 2, < 3",
28
28
  "google-cloud-texttospeech >= 2.27, < 3",
29
29
  "google-genai >= v1.23.0",
30
- "livekit-agents>=1.2.3",
30
+ "livekit-agents>=1.2.5",
31
31
  ]
32
32
 
33
33
  [project.urls]