Run a Kokoro Text to Speech Locally or as a High-throughput Server
🎙️Custom voice AI (ASR & TTS) for enterprise — you own the model: trelis.com/voice-ai
📜Get repo access at Trelis.com/ADVANCED-audio
🗝️ Get Trelis All Access (Trelis.com/All-Access)
1. Access all SEVEN Trelis Github Repos (-robotics, -vision, -evals, -fine-tuning, -inference, -voice, -time-series)
2. Support via Github Issues & Trelis’ Private Discord
3. Early access to Trelis videos via Discord
💰Runpod Affiliate Link, incl. bonus on signup: https://runpod.io?ref=jmfkcdio
Tip: If you subscribe here on YouTube, click the bell to be notified of new vids
💡 Done-for-you Custom Fine-tuning Services
Learn More: https://trelis.com/fine-tuning-services/
💸 Starting a New Project/Venture?
Apply for a Trelis Grant: https://trelis.com/trelis-ai-grants/
📧 Get Trelis AI Tutorials by Email
Subscribe on Substack: https://trelis.substack.com
Video Links:
Server: https://github.com/remsky/Kokoro-FastAPI
Kokoro HF: https://huggingface.co/hexgrad/Kokoro... | https://huggingface.co/hexgrad/Kokoro...
TIMESTAMPS:
0:00 Generate voices with various accents with Kokoro
0:15 Kokoro - a small, permissively licensed text to speech model
2:34 Video Resources and Kokoro Setup
2:58 My recommendations on Text to Speech models for inference and fine-tuning
3:56 One-click affiliate template for a high throughput Kokoro Server: https://console.runpod.io/deploy?temp...
4:31 Run Kokoro locally
8:29 Synthetic data generation via a server
9:58 Benchmarking Server Throughput
12:38 Conclusion