Pocket TTS integration for Vision Agents - lightweight CPU-based text-to-speech
Project description
Pocket TTS Plugin
A lightweight Text-to-Speech (TTS) plugin for Vision Agents powered by Kyutai's Pocket TTS model. Runs efficiently on CPU with low latency (~200ms) and supports voice cloning.
Features
- Runs on CPU - no GPU required
- Small model size (100M parameters)
- Low latency (~200ms to first audio)
- Voice cloning support
- Built-in voice selection
Installation
uv add "vision-agents[pocket]"
# or directly
uv add vision-agents-plugins-pocket
Usage
from vision_agents.plugins import pocket
# Create TTS with default voice
tts = pocket.TTS()
# Or specify a built-in voice
tts = pocket.TTS(voice="marius")
# Or use a custom voice for cloning
tts = pocket.TTS(voice="path/to/your/voice.wav")
Configuration
| Parameter | Description | Values |
|---|---|---|
voice |
Built-in voice name or path to custom wav file | "alba" (default), "marius", "javert", "jean", "fantine", "cosette", "eponine", "azelma", or custom path |
Built-in Voices
alba- Default voicemariusjavertjeanfantinecosetteeponineazelma
Dependencies
- pocket-tts>=0.1.0
- PyTorch 2.5+
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vision_agents_plugins_pocket-0.5.1.tar.gz.
File metadata
- Download URL: vision_agents_plugins_pocket-0.5.1.tar.gz
- Upload date:
- Size: 3.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.6 {"installer":{"name":"uv","version":"0.10.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f8fe42dab5c2174f0c971c82a6650be8b80c99674e1c95454428202752e6e27f
|
|
| MD5 |
06afe30d26d826b047c9725b11e238c1
|
|
| BLAKE2b-256 |
e8ad5198b6308fbc7c5956d3a64c60ff4bef26763c83bcd5b620468143a4bf59
|
File details
Details for the file vision_agents_plugins_pocket-0.5.1-py3-none-any.whl.
File metadata
- Download URL: vision_agents_plugins_pocket-0.5.1-py3-none-any.whl
- Upload date:
- Size: 8.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.10.6 {"installer":{"name":"uv","version":"0.10.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fbb0305bf3a87f733d3076bb5a26b73fa96c6272f871b047e816be72c0e5f7f0
|
|
| MD5 |
806770ef52513e9496bbbc79ef13254b
|
|
| BLAKE2b-256 |
d55e484a069f6647d0fda3b54de06858beac0d8249807b2eccc0a7987451c890
|
