swarmauri_agent_texttospeech 0.11.0.dev5__tar.gz → 0.11.0.dev6__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.
- {swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/PKG-INFO +5 -1
- {swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/README.md +4 -0
- {swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/pyproject.toml +3 -1
- {swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/swarmauri_agent_texttospeech/TextToSpeechAgent.py +22 -11
- {swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/LICENSE +0 -0
- {swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/swarmauri_agent_texttospeech/__init__.py +0 -0
{swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/PKG-INFO
RENAMED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: swarmauri_agent_texttospeech
|
|
3
|
-
Version: 0.11.0.
|
|
3
|
+
Version: 0.11.0.dev6
|
|
4
4
|
Summary: Stateless Swarmauri agent for converting independent text prompts into audio through any TTSBase provider.
|
|
5
5
|
License-Expression: Apache-2.0
|
|
6
6
|
License-File: LICENSE
|
|
@@ -133,3 +133,7 @@ should follow the repository contribution and style guides.
|
|
|
133
133
|
|
|
134
134
|
Apache-2.0
|
|
135
135
|
|
|
136
|
+
Provider instances are validated against TTSBase at call-time construction, so
|
|
137
|
+
providers imported after the agent class remain usable. Serialized providers
|
|
138
|
+
retain their concrete fields; import that provider before deserialization.
|
|
139
|
+
|
{swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/README.md
RENAMED
|
@@ -106,3 +106,7 @@ should follow the repository contribution and style guides.
|
|
|
106
106
|
## License
|
|
107
107
|
|
|
108
108
|
Apache-2.0
|
|
109
|
+
|
|
110
|
+
Provider instances are validated against TTSBase at call-time construction, so
|
|
111
|
+
providers imported after the agent class remain usable. Serialized providers
|
|
112
|
+
retain their concrete fields; import that provider before deserialization.
|
{swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/pyproject.toml
RENAMED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "swarmauri_agent_texttospeech"
|
|
3
|
-
version = "0.11.0.
|
|
3
|
+
version = "0.11.0.dev6"
|
|
4
4
|
description = "Stateless Swarmauri agent for converting independent text prompts into audio through any TTSBase provider."
|
|
5
5
|
license = "Apache-2.0"
|
|
6
6
|
readme = "README.md"
|
|
@@ -38,6 +38,7 @@ keywords = [
|
|
|
38
38
|
|
|
39
39
|
[tool.uv.sources]
|
|
40
40
|
swarmauri_core = { workspace = true }
|
|
41
|
+
swarmauri_tts_openai = { workspace = true }
|
|
41
42
|
swarmauri_base = { workspace = true }
|
|
42
43
|
swarmauri_tts_elevenlabs_dialogue = { workspace = true }
|
|
43
44
|
swarmauri_tts_gemini_dialogue = { workspace = true }
|
|
@@ -56,6 +57,7 @@ build-backend = "poetry.core.masonry.api"
|
|
|
56
57
|
|
|
57
58
|
[dependency-groups]
|
|
58
59
|
dev = [
|
|
60
|
+
"swarmauri_tts_openai>=0.1.0a2,<0.2",
|
|
59
61
|
"swarmauri_tts_elevenlabs_dialogue>=0.1.0a1,<0.2",
|
|
60
62
|
"swarmauri_tts_gemini_dialogue>=0.1.0a1,<0.2",
|
|
61
63
|
"pytest>=8.0",
|
|
@@ -7,9 +7,15 @@ from collections.abc import Sequence
|
|
|
7
7
|
from pathlib import Path
|
|
8
8
|
from typing import Any, Dict, List, Literal, Optional, Union
|
|
9
9
|
|
|
10
|
-
from pydantic import
|
|
11
|
-
|
|
12
|
-
|
|
10
|
+
from pydantic import (
|
|
11
|
+
BaseModel,
|
|
12
|
+
ConfigDict,
|
|
13
|
+
Field,
|
|
14
|
+
SerializeAsAny,
|
|
15
|
+
field_validator,
|
|
16
|
+
)
|
|
17
|
+
|
|
18
|
+
from swarmauri_base.ComponentBase import ComponentBase
|
|
13
19
|
from swarmauri_base.agents.AgentBase import AgentBase
|
|
14
20
|
from swarmauri_base.tts.TTSBase import TTSBase
|
|
15
21
|
from swarmauri_core.messages.IMessage import IMessage
|
|
@@ -21,23 +27,28 @@ class TextToSpeechAgent(AgentBase):
|
|
|
21
27
|
|
|
22
28
|
llm: None = Field(default=None, exclude=True)
|
|
23
29
|
llm_kwargs: None = Field(default=None, exclude=True)
|
|
24
|
-
tts:
|
|
30
|
+
tts: SerializeAsAny[TTSBase]
|
|
25
31
|
output_path: str = "output.mp3"
|
|
26
32
|
tts_kwargs: Dict[str, Any] = Field(default_factory=dict)
|
|
27
33
|
model_config = ConfigDict(extra="forbid", arbitrary_types_allowed=True)
|
|
28
34
|
type: Literal["TextToSpeechAgent"] = "TextToSpeechAgent"
|
|
29
35
|
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
36
|
+
@field_validator("tts", mode="before")
|
|
37
|
+
@classmethod
|
|
38
|
+
def _restore_tts(cls, value):
|
|
39
|
+
"""Resolve serialized providers at validation time, after discovery."""
|
|
40
|
+
if not isinstance(value, dict):
|
|
41
|
+
return value
|
|
42
|
+
type_name = value.get("type")
|
|
35
43
|
registry = TTSBase._registry.get("TTSBase", {})
|
|
36
44
|
tts_class = registry.get("subtypes", {}).get(type_name)
|
|
37
45
|
if tts_class is None and type_name == "TTSBase":
|
|
38
46
|
tts_class = registry.get("model_cls", TTSBase)
|
|
39
|
-
if tts_class is
|
|
40
|
-
|
|
47
|
+
if tts_class is None:
|
|
48
|
+
raise ValueError(
|
|
49
|
+
"Import the serialized TTS provider before loading it."
|
|
50
|
+
)
|
|
51
|
+
return tts_class.model_validate(value)
|
|
41
52
|
|
|
42
53
|
def exec(
|
|
43
54
|
self,
|
{swarmauri_agent_texttospeech-0.11.0.dev5 → swarmauri_agent_texttospeech-0.11.0.dev6}/LICENSE
RENAMED
|
File without changes
|