chichi-speech 0.1.0__py3-none-any.whl → 0.1.1__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.
- {chichi_speech-0.1.0.dist-info → chichi_speech-0.1.1.dist-info}/METADATA +7 -13
- {chichi_speech-0.1.0.dist-info → chichi_speech-0.1.1.dist-info}/RECORD +4 -4
- {chichi_speech-0.1.0.dist-info → chichi_speech-0.1.1.dist-info}/WHEEL +0 -0
- {chichi_speech-0.1.0.dist-info → chichi_speech-0.1.1.dist-info}/entry_points.txt +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: chichi-speech
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.1
|
|
4
4
|
Summary: Qwen3 TTS Service with Voice Cloning
|
|
5
5
|
Requires-Python: >=3.10
|
|
6
6
|
Requires-Dist: fastapi
|
|
@@ -15,6 +15,7 @@ Provides-Extra: dev
|
|
|
15
15
|
Requires-Dist: build; extra == 'dev'
|
|
16
16
|
Requires-Dist: httpx; extra == 'dev'
|
|
17
17
|
Requires-Dist: pytest; extra == 'dev'
|
|
18
|
+
Requires-Dist: twine; extra == 'dev'
|
|
18
19
|
Description-Content-Type: text/markdown
|
|
19
20
|
|
|
20
21
|
# Chichi Speech
|
|
@@ -23,6 +24,8 @@ Description-Content-Type: text/markdown
|
|
|
23
24
|
|
|
24
25
|
Chichi Speech provides a robust REST API and CLI tools for text-to-speech synthesis, featuring efficient voice cloning capabilities. It is designed to be easily deployed or integrated into other AI agents and workflows.
|
|
25
26
|
|
|
27
|
+
Acknowledgement: This project is just a simple wrapper of [Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS), the SOTA TTS model as of 2/5/2025.
|
|
28
|
+
|
|
26
29
|
## Features
|
|
27
30
|
|
|
28
31
|
- **High Quality**: Utilizes the Qwen3-TTS model for state-of-the-art speech synthesis.
|
|
@@ -33,18 +36,10 @@ Chichi Speech provides a robust REST API and CLI tools for text-to-speech synthe
|
|
|
33
36
|
|
|
34
37
|
## Installation
|
|
35
38
|
|
|
36
|
-
Prerequisites: `
|
|
39
|
+
Prerequisites: `python >= 3.10`.
|
|
37
40
|
|
|
38
41
|
```bash
|
|
39
|
-
|
|
40
|
-
export CHICHI_SPEECH_ENV="~/chichi-speech/.venv"
|
|
41
|
-
git clone https://github.com/yourusername/chichi-speech.git $CHICHI_SPEECH_HOME
|
|
42
|
-
cd $CHICHI_SPEECH_HOME
|
|
43
|
-
|
|
44
|
-
uv venv $CHICHI_SPEECH_ENV --python 3.10
|
|
45
|
-
source $CHICHI_SPEECH_ENV/bin/activate
|
|
46
|
-
|
|
47
|
-
uv pip install -e .
|
|
42
|
+
pip install chichi-speech
|
|
48
43
|
```
|
|
49
44
|
|
|
50
45
|
## Usage
|
|
@@ -55,7 +50,6 @@ The service runs on port **9090** by default.
|
|
|
55
50
|
|
|
56
51
|
```bash
|
|
57
52
|
# Start the server (runs in foreground, use & for background or a separate terminal)
|
|
58
|
-
source $$CHICHI_SPEECH_ENV/bin/activate
|
|
59
53
|
chichi-speech-server
|
|
60
54
|
# OR specify the port explicitly
|
|
61
55
|
chichi-speech-server --port 9090 --host 0.0.0.0
|
|
@@ -91,7 +85,7 @@ curl -X POST "http://localhost:9090/synthesize" \
|
|
|
91
85
|
|
|
92
86
|
Install dev dependencies:
|
|
93
87
|
```bash
|
|
94
|
-
|
|
88
|
+
pip install -e ".[dev]"
|
|
95
89
|
```
|
|
96
90
|
|
|
97
91
|
Run tests:
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
chichi_speech/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
2
2
|
chichi_speech/client.py,sha256=GYIxqKy1ONsOxNMx83gMOT1cM6K0rdjWSR_lnPiLk8U,1381
|
|
3
3
|
chichi_speech/server.py,sha256=JnC7A7casb3q_HRot9sSjgA_41E-H7lnJHr_tHOtSMg,4204
|
|
4
|
-
chichi_speech-0.1.
|
|
5
|
-
chichi_speech-0.1.
|
|
6
|
-
chichi_speech-0.1.
|
|
7
|
-
chichi_speech-0.1.
|
|
4
|
+
chichi_speech-0.1.1.dist-info/METADATA,sha256=7_L8PqncY38Uj03QhEYbIXyWpLHz3icT_bkweUrw-xE,2696
|
|
5
|
+
chichi_speech-0.1.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
|
|
6
|
+
chichi_speech-0.1.1.dist-info/entry_points.txt,sha256=tRZ0iWPkkhzyEEQUSnGhyjbFJwxX49JkyqfU5xPR9yM,116
|
|
7
|
+
chichi_speech-0.1.1.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|