TulgaTTS
TulgaTTS - A library for synthesizing text-to-speech (TTS) with various popular voices in Kazakhstan.
Installation
# Via pip (in the future)
pip install tulgatts
# For audio playback (optional):
pip install -e .[audio]
Getting Started
-
Obtain your token:
-
⚠️ DO NOT SHARE YOUR TOKEN! It is required to send requests from your account.
-
Open link https://character.ai/chat/2WPyJRflV_4nTx6_-tuNrhkiiqhDyOsn9O25BR1sDO8
-
Open Developer Tools in your browser (usually F12).
-
Go to the Network tab.
-
Refresh the page or send a message to any character.
-
In the list of network requests, click on any request (for example, to
/settings).
-
Go to the Headers section.
-
Find the Authorization header. It will look like:
Authorization: Token <your_token_here> -
Copy only the token part (after
Token). -
Set the
CHARACTER_AI_TOKENenvironment variable or create a.envfile in the project root and addCHARACTER_AI_TOKEN=your_copied_token.
-
-
Use the library.
Usage Examples
You can use the library in several ways. For simple scripts, use the synchronous method; for async applications, use the async/await method.
1. The simplest usage
from tulgatts import TulgaTTS
# Create a client (default voice – Tokaev)
client = TulgaTTS(api_token="CHARACTER_AI_TOKEN", voice="Tokaev")
# 1. Speak with the default voice and save to file
client.say("This is an example created with this class")
2. Synchronous usage
import os
from tulgatts import TulgaTTS
from dotenv import load_dotenv
# Load token from .env
load_dotenv()
api_token = os.getenv("CHARACTER_AI_TOKEN")
def sync_say_usage():
if not api_token:
print("❌ No token!")
return
try:
tts_client = TulgaTTS(api_token=api_token, voice='Tokaev')
print(f"✅ Client ready with voice '{tts_client.voice}'.")
tts_client.say("Synchronous example.", output_file="sync_example.mp3")
print("🎧 File ready: sync_example.mp3")
except Exception as e:
print(f"⚠️ Error occurred: {e}")
if __name__ == "__main__":
print("2. Synchronous example...")
sync_say_usage()
print("-" * 20)
3. Asynchronous usage
import os, asyncio
from tulgatts import TulgaTTS
from dotenv import load_dotenv
# Load token from .env
load_dotenv()
api_token = os.getenv("CHARACTER_AI_TOKEN")
async def advanced_async_say():
if not api_token: return print("No token!")
try:
tts_client = TulgaTTS(api_token=api_token)
print(f"Client ready with voice '{tts_client.voice}'.")
await tts_client.say_async("Third example, part one.", voice="Tokaev", output_file="advanced_async1.mp3", play_audio=True)
except Exception as e: print(f"Error: {e}")
if __name__ == "__main__":
print("\n3. More advanced async example...")
asyncio.run(advanced_async_say())
print("All examples completed.")
Available Voices
The library comes with the following pre-configured voices:
-
Nursultan Nazarbaev
-
Tokaev
-
Pavel Durov
-
Nurlan Saburov
-
Putin
-
Skriptonit
-
Elon Musk
-
Albert E
-
Yandex Alica
-
J.A.R.V.I.S
-
Tony Stark
Note: Sometimes TulgaTTS may not synthesize your expected text. This issue is being worked on.
Special thanks to PyCharacterAI for enabling TTS with Character AI voices.
Authors
-
David Suragan (TulgaTTS)
-
Gemini AI
License
MIT
Metadata
Release files for tulgatts 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| tulgatts-0.1.3.tar.gz | 9.8 kB | Without provenance | Details for tulgatts-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| tulgatts-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for tulgatts-0.1.3-py3-none-any.whl |
Total release size: 18.2 kB
Release files / tulgatts-0.1.3.tar.gz
| Download URL | tulgatts-0.1.3.tar.gz |
|---|---|
| Size | 9.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2c17a9b933db081e020a3734fe4d27d9032a8b3a503f9e544e069a07a5976a25
|
|
BLAKE2b-256 checksum How to use checksums |
48ee5b52059f7fe5c06ebf35732736f475c24527907bcccb98019be3923a4c32
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.4
|
Release files / tulgatts-0.1.3-py3-none-any.whl
| Download URL | tulgatts-0.1.3-py3-none-any.whl |
|---|---|
| Size | 8.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a1221dc5e8be76806cb17609a2120947a22c46b1d1852505b8457a26bb571f06
|
|
BLAKE2b-256 checksum How to use checksums |
db7cfef31c7baae620049d30c45cde062ee39f8899c88815011dbe9c2dbc7e2c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.4
|
Security for tulgatts 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.