livekit-plugins-cartesia 0.4.10__py3-none-any.whl → 1.0.0.dev4__py3-none-any.whl
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.
- livekit/plugins/cartesia/models.py +1 -1
- livekit/plugins/cartesia/tts.py +11 -22
- livekit/plugins/cartesia/version.py +1 -1
- {livekit_plugins_cartesia-0.4.10.dist-info → livekit_plugins_cartesia-1.0.0.dev4.dist-info}/METADATA +10 -20
- livekit_plugins_cartesia-1.0.0.dev4.dist-info/RECORD +9 -0
- {livekit_plugins_cartesia-0.4.10.dist-info → livekit_plugins_cartesia-1.0.0.dev4.dist-info}/WHEEL +1 -2
- livekit_plugins_cartesia-0.4.10.dist-info/RECORD +0 -10
- livekit_plugins_cartesia-0.4.10.dist-info/top_level.txt +0 -1
@@ -8,7 +8,7 @@ TTSEncoding = Literal[
|
|
8
8
|
# "pcm_alaw",
|
9
9
|
]
|
10
10
|
|
11
|
-
TTSModels = Literal["sonic
|
11
|
+
TTSModels = Literal["sonic-english", "sonic-multilingual"]
|
12
12
|
TTSLanguages = Literal["en", "es", "fr", "de", "pt", "zh", "ja"]
|
13
13
|
TTSDefaultVoiceId = "794f9389-aac1-45b6-b726-9d9369183238"
|
14
14
|
TTSVoiceSpeed = Literal["fastest", "fast", "normal", "slow", "slowest"]
|
livekit/plugins/cartesia/tts.py
CHANGED
@@ -20,9 +20,10 @@ import json
|
|
20
20
|
import os
|
21
21
|
import weakref
|
22
22
|
from dataclasses import dataclass
|
23
|
-
from typing import Any
|
23
|
+
from typing import Any
|
24
24
|
|
25
25
|
import aiohttp
|
26
|
+
|
26
27
|
from livekit.agents import (
|
27
28
|
APIConnectionError,
|
28
29
|
APIConnectOptions,
|
@@ -34,13 +35,7 @@ from livekit.agents import (
|
|
34
35
|
)
|
35
36
|
|
36
37
|
from .log import logger
|
37
|
-
from .models import
|
38
|
-
TTSDefaultVoiceId,
|
39
|
-
TTSEncoding,
|
40
|
-
TTSModels,
|
41
|
-
TTSVoiceEmotion,
|
42
|
-
TTSVoiceSpeed,
|
43
|
-
)
|
38
|
+
from .models import TTSDefaultVoiceId, TTSEncoding, TTSModels, TTSVoiceEmotion, TTSVoiceSpeed
|
44
39
|
|
45
40
|
API_AUTH_HEADER = "X-API-Key"
|
46
41
|
API_VERSION_HEADER = "Cartesia-Version"
|
@@ -73,7 +68,7 @@ class TTS(tts.TTS):
|
|
73
68
|
def __init__(
|
74
69
|
self,
|
75
70
|
*,
|
76
|
-
model: TTSModels | str = "sonic
|
71
|
+
model: TTSModels | str = "sonic",
|
77
72
|
language: str = "en",
|
78
73
|
encoding: TTSEncoding = "pcm_s16le",
|
79
74
|
voice: str | list[float] = TTSDefaultVoiceId,
|
@@ -90,7 +85,7 @@ class TTS(tts.TTS):
|
|
90
85
|
See https://docs.cartesia.ai/reference/web-socket/stream-speech/stream-speech for more details on the the Cartesia API.
|
91
86
|
|
92
87
|
Args:
|
93
|
-
model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-
|
88
|
+
model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-english".
|
94
89
|
language (str, optional): The language code for synthesis. Defaults to "en".
|
95
90
|
encoding (TTSEncoding, optional): The audio encoding format. Defaults to "pcm_s16le".
|
96
91
|
voice (str | list[float], optional): The voice ID or embedding array.
|
@@ -137,9 +132,7 @@ class TTS(tts.TTS):
|
|
137
132
|
url = self._opts.get_ws_url(
|
138
133
|
f"/tts/websocket?api_key={self._opts.api_key}&cartesia_version={API_VERSION}"
|
139
134
|
)
|
140
|
-
return await asyncio.wait_for(
|
141
|
-
session.ws_connect(url), self._conn_options.timeout
|
142
|
-
)
|
135
|
+
return await asyncio.wait_for(session.ws_connect(url), self._conn_options.timeout)
|
143
136
|
|
144
137
|
async def _close_ws(self, ws: aiohttp.ClientWebSocketResponse):
|
145
138
|
await ws.close()
|
@@ -169,7 +162,7 @@ class TTS(tts.TTS):
|
|
169
162
|
and emotion. If any parameter is not provided, the existing value will be retained.
|
170
163
|
|
171
164
|
Args:
|
172
|
-
model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-
|
165
|
+
model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-english".
|
173
166
|
language (str, optional): The language code for synthesis. Defaults to "en".
|
174
167
|
voice (str | list[float], optional): The voice ID or embedding array.
|
175
168
|
speed (TTSVoiceSpeed | float, optional): Voice Control - Speed (https://docs.cartesia.ai/user-guides/voice-control)
|
@@ -186,7 +179,7 @@ class TTS(tts.TTS):
|
|
186
179
|
self,
|
187
180
|
text: str,
|
188
181
|
*,
|
189
|
-
conn_options:
|
182
|
+
conn_options: APIConnectOptions | None = None,
|
190
183
|
) -> ChunkedStream:
|
191
184
|
return ChunkedStream(
|
192
185
|
tts=self,
|
@@ -196,16 +189,12 @@ class TTS(tts.TTS):
|
|
196
189
|
session=self._ensure_session(),
|
197
190
|
)
|
198
191
|
|
199
|
-
def stream(
|
200
|
-
|
201
|
-
) -> "SynthesizeStream":
|
202
|
-
stream = SynthesizeStream(
|
192
|
+
def stream(self, *, conn_options: APIConnectOptions | None = None) -> SynthesizeStream:
|
193
|
+
return SynthesizeStream(
|
203
194
|
tts=self,
|
204
195
|
pool=self._pool,
|
205
196
|
opts=self._opts,
|
206
197
|
)
|
207
|
-
self._streams.add(stream)
|
208
|
-
return stream
|
209
198
|
|
210
199
|
async def aclose(self) -> None:
|
211
200
|
for stream in list(self._streams):
|
@@ -225,7 +214,7 @@ class ChunkedStream(tts.ChunkedStream):
|
|
225
214
|
input_text: str,
|
226
215
|
opts: _TTSOptions,
|
227
216
|
session: aiohttp.ClientSession,
|
228
|
-
conn_options:
|
217
|
+
conn_options: APIConnectOptions | None = None,
|
229
218
|
) -> None:
|
230
219
|
super().__init__(tts=tts, input_text=input_text, conn_options=conn_options)
|
231
220
|
self._opts, self._session = opts, session
|
{livekit_plugins_cartesia-0.4.10.dist-info → livekit_plugins_cartesia-1.0.0.dev4.dist-info}/METADATA
RENAMED
@@ -1,35 +1,25 @@
|
|
1
|
-
Metadata-Version: 2.
|
1
|
+
Metadata-Version: 2.4
|
2
2
|
Name: livekit-plugins-cartesia
|
3
|
-
Version: 0.
|
3
|
+
Version: 1.0.0.dev4
|
4
4
|
Summary: LiveKit Agents Plugin for Cartesia
|
5
|
-
Home-page: https://github.com/livekit/agents
|
6
|
-
License: Apache-2.0
|
7
5
|
Project-URL: Documentation, https://docs.livekit.io
|
8
6
|
Project-URL: Website, https://livekit.io/
|
9
7
|
Project-URL: Source, https://github.com/livekit/agents
|
10
|
-
|
8
|
+
Author-email: LiveKit <support@livekit.io>
|
9
|
+
License-Expression: Apache-2.0
|
10
|
+
Keywords: audio,livekit,realtime,video,webrtc
|
11
11
|
Classifier: Intended Audience :: Developers
|
12
12
|
Classifier: License :: OSI Approved :: Apache Software License
|
13
|
-
Classifier: Topic :: Multimedia :: Sound/Audio
|
14
|
-
Classifier: Topic :: Multimedia :: Video
|
15
|
-
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
16
13
|
Classifier: Programming Language :: Python :: 3
|
14
|
+
Classifier: Programming Language :: Python :: 3 :: Only
|
17
15
|
Classifier: Programming Language :: Python :: 3.9
|
18
16
|
Classifier: Programming Language :: Python :: 3.10
|
19
|
-
Classifier:
|
17
|
+
Classifier: Topic :: Multimedia :: Sound/Audio
|
18
|
+
Classifier: Topic :: Multimedia :: Video
|
19
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
20
20
|
Requires-Python: >=3.9.0
|
21
|
+
Requires-Dist: livekit-agents>=1.0.0.dev4
|
21
22
|
Description-Content-Type: text/markdown
|
22
|
-
Requires-Dist: livekit-agents<1.0.0,>=0.12.16
|
23
|
-
Dynamic: classifier
|
24
|
-
Dynamic: description
|
25
|
-
Dynamic: description-content-type
|
26
|
-
Dynamic: home-page
|
27
|
-
Dynamic: keywords
|
28
|
-
Dynamic: license
|
29
|
-
Dynamic: project-url
|
30
|
-
Dynamic: requires-dist
|
31
|
-
Dynamic: requires-python
|
32
|
-
Dynamic: summary
|
33
23
|
|
34
24
|
# LiveKit Plugins Cartesia
|
35
25
|
|
@@ -0,0 +1,9 @@
|
|
1
|
+
livekit/plugins/cartesia/__init__.py,sha256=UTa6Q7IxhRBCwPftowHEUDvmBg99J_UjGS_yxTzKD7g,1095
|
2
|
+
livekit/plugins/cartesia/log.py,sha256=4Mnhjng_DU1dIWP9IWjIQGZ67EV3LnQhWMWCHVudJbo,71
|
3
|
+
livekit/plugins/cartesia/models.py,sha256=56CJgo7my-w-vpedir_ImV_aqKASeLihE5DbcCCgGJI,950
|
4
|
+
livekit/plugins/cartesia/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
5
|
+
livekit/plugins/cartesia/tts.py,sha256=Zub4MXXVXQgV0t6al_uidDWH3BTVaYftyVbAFbkTU-U,13999
|
6
|
+
livekit/plugins/cartesia/version.py,sha256=koM_bT4QbztrKQ60Gjg7V4oe99CuxgGcpuUtWMOEKqU,605
|
7
|
+
livekit_plugins_cartesia-1.0.0.dev4.dist-info/METADATA,sha256=DxLT1utt8LaD23sG9baagoFSCnS6SwhRzPILssbq82Y,1265
|
8
|
+
livekit_plugins_cartesia-1.0.0.dev4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
|
9
|
+
livekit_plugins_cartesia-1.0.0.dev4.dist-info/RECORD,,
|
@@ -1,10 +0,0 @@
|
|
1
|
-
livekit/plugins/cartesia/__init__.py,sha256=UTa6Q7IxhRBCwPftowHEUDvmBg99J_UjGS_yxTzKD7g,1095
|
2
|
-
livekit/plugins/cartesia/log.py,sha256=4Mnhjng_DU1dIWP9IWjIQGZ67EV3LnQhWMWCHVudJbo,71
|
3
|
-
livekit/plugins/cartesia/models.py,sha256=KGY-r2luJuUNY6a3nnB0Rx-5Td12hikk-GtYLnqvysE,977
|
4
|
-
livekit/plugins/cartesia/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
5
|
-
livekit/plugins/cartesia/tts.py,sha256=cOoNFXNlw2NFN5o6PgLTccu_-y_W0MTAwNciNDtxdd8,14128
|
6
|
-
livekit/plugins/cartesia/version.py,sha256=EAXwrHdOWRivmdK-RTQl1YBemh0E8ui_JHvG9dT490M,601
|
7
|
-
livekit_plugins_cartesia-0.4.10.dist-info/METADATA,sha256=TXT6xGvQ3of6Gl9PyCCYLrurnkDdfyiOjzyrXC0gga4,1471
|
8
|
-
livekit_plugins_cartesia-0.4.10.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
|
9
|
-
livekit_plugins_cartesia-0.4.10.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
|
10
|
-
livekit_plugins_cartesia-0.4.10.dist-info/RECORD,,
|
@@ -1 +0,0 @@
|
|
1
|
-
livekit
|