Interweave
Voice I/O MCP server for Claude Code. Speak and listen through your mic and speakers.
Uses Kokoro MLX (TTS), Parakeet MLX (STT), and Silero VAD. Runs locally on Apple Silicon.
Install
curl -fsSL https://raw.githubusercontent.com/EndlessHoper/interweave/main/install.sh | bash
This will:
- Install Python dependencies (~4.5GB total, includes torch and ML models)
- Download ML models (Kokoro TTS, Parakeet STT, Silero VAD)
- Register interweave with Claude Code
After install, start a new Claude Code session and talk.
Manual install
If you prefer to install step by step:
uv tool install --python ">=3.11" interweave
claude mcp add interweave -- interweave
Codex
uv tool install --python ">=3.11" interweave
codex mcp add interweave -- interweave
OpenCode
uv tool install --python ">=3.11" interweave
Then add to opencode.json:
{
"mcp": {
"interweave": {
"type": "local",
"command": ["interweave"],
"enabled": true
}
}
}
Uninstall
uv tool uninstall interweave
claude mcp remove interweave
# Optional: remove cached ML models (~2GB)
rm -rf ~/.cache/huggingface/hub/models--mlx-community--Kokoro-82M-bf16
rm -rf ~/.cache/huggingface/hub/models--animaslabs--parakeet-tdt-0.6b-v3-mlx
rm -rf ~/.cache/torch/hub/snakers4_silero-vad_master
Requirements
- macOS with Apple Silicon
- Python 3.11+
- Microphone and speakers
- uv (
curl -LsSf https://astral.sh/uv/install.sh | sh)
Metadata
Release files for interweave 0.2.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| interweave-0.2.5.tar.gz | 7.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| interweave-0.2.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 14.3 kB
Release files / interweave-0.2.5.tar.gz
| Download URL | interweave-0.2.5.tar.gz |
|---|---|
| Size | 7.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cf88ba203067d5bc0d97115d22b7bc31c59c71b9fbb58c0e2c176c766a5a2336
|
|
BLAKE2b-256 checksum How to use checksums |
7495938e5ea51a8b83618740411586c06c1d2760b9f2a9c3a036b7dd2736d616
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 9, 2026.
Transparency logRelease files / interweave-0.2.5-py3-none-any.whl
| Download URL | interweave-0.2.5-py3-none-any.whl |
|---|---|
| Size | 7.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6cc9acce858da6be4b752cce9e0ea39dfb4bb45cd17407bac60f875f87e6357d
|
|
BLAKE2b-256 checksum How to use checksums |
1014be941555af7c3815de53c5ce33a5eed3a5c7db5e6f0bf9e04ba78e6eb3fd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Feb 9, 2026.
Transparency log