From sundial-org-awesome-openclaw-skills-4
Transcribes audio files to text locally using NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, auto-detects 25 languages, provides OpenAI-compatible API for offline processing.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin sundial-org-awesome-openclaw-skills-4This skill uses the workspace's default tool permissions.
Local transcription using NVIDIA Parakeet TDT 0.6B v3 with ONNX Runtime.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Local transcription using NVIDIA Parakeet TDT 0.6B v3 with ONNX Runtime. Runs on CPU — no GPU required. ~30x faster than realtime.
# Clone the repo
git clone https://github.com/groxaxo/parakeet-tdt-0.6b-v3-fastapi-openai.git
cd parakeet-tdt-0.6b-v3-fastapi-openai
# Run with Docker (recommended)
docker compose up -d parakeet-cpu
# Or run directly with Python
pip install -r requirements.txt
uvicorn app.main:app --host 0.0.0.0 --port 5000
Default port is 5000. Set PARAKEET_URL to override (e.g., http://localhost:5092).
OpenAI-compatible API at $PARAKEET_URL (default: http://localhost:5000).
# Transcribe audio file (plain text)
curl -X POST $PARAKEET_URL/v1/audio/transcriptions \
-F "file=@/path/to/audio.mp3" \
-F "response_format=text"
# Get timestamps and segments
curl -X POST $PARAKEET_URL/v1/audio/transcriptions \
-F "file=@/path/to/audio.mp3" \
-F "response_format=verbose_json"
# Generate subtitles (SRT)
curl -X POST $PARAKEET_URL/v1/audio/transcriptions \
-F "file=@/path/to/audio.mp3" \
-F "response_format=srt"
import os
from openai import OpenAI
client = OpenAI(
base_url=os.getenv("PARAKEET_URL", "http://localhost:5000") + "/v1",
api_key="not-needed"
)
with open("audio.mp3", "rb") as f:
transcript = client.audio.transcriptions.create(
model="parakeet-tdt-0.6b-v3",
file=f,
response_format="text"
)
print(transcript)
| Format | Output |
|---|---|
text | Plain text |
json | {"text": "..."} |
verbose_json | Segments with timestamps and words |
srt | SRT subtitles |
vtt | WebVTT subtitles |
English, Spanish, French, German, Italian, Portuguese, Polish, Russian, Ukrainian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Czech, Romanian, Hungarian, Bulgarian, Slovak, Croatian, Lithuanian, Latvian, Estonian, Slovenian
Language is auto-detected — no configuration needed.
Open $PARAKEET_URL in a browser for drag-and-drop transcription UI.
# Check status
docker ps --filter "name=parakeet"
# View logs
docker logs -f <container-name>
# Restart
docker compose restart
# Stop
docker compose down