AIQB
TutorialsOrdinary

Four on-device TTS models on one CPU core: LinnetTTS, Piper, Kokoro, pocket-tts

Source: DEV Community·

Summary

Most CPU TTS writeups benchmark one model in isolation. When you are building a voice product, that...
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-c0d6f756218c317529c2c1c7
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
My agents kept dropping what resisted. 10 of my 19 vetoes were about that.
On September 30, an agent was building a catalogue of every setting in our back-office, nearly three...
Source: DEV Community
TutorialsOrdinary
Build a JTL Cloud App with an AI Agent
What if you could turn a short prompt into a working JTL Cloud App, complete with access to real ERP...
Source: DEV Community
TutorialsOrdinary
The Complete Guide to RAG, MCP, LangGraph, Embeddings, and Beyond
A practical field guide to the concepts, architectures, and free-versus-professional tools behind...
Source: DEV Community
TutorialsOrdinary
Moved Your Repo Folder? Every Agent Worktree Broke. git worktree repair Fixes It
Worktrees link to your repo by absolute path, so a mv breaks every agent's checkout. Fix it with git worktree repair, then prevent it with relative paths.
Source: DEV Community
TutorialsOrdinary
Turning GPT GIFs into a cat film: what smoothing fixed, and what it didn’t
A cat crosses a room, jumps onto a windowsill, watches a bird, curls up and falls asleep. That became...
Source: DEV Community · GPT
TutorialsOrdinary
Pourquoi git checkout ne peut-il pas annuler ce qu'un agent de code IA a modifié ?
Quand un agent IA modifie des fichiers de votre projet et casse quelque chose, le réflexe est git...
Source: DEV Community
TutorialsOrdinary
Claude Code was mailing your email address to every website it visited: the User-Agent leak, the 5-month system-prompt issue, and the 5-point check
Claude Code put your account email in the User-Agent header of its web requests, so every server log on the agent's path harvested a scam-ready lead, and the same email ships in the system prompt of every session, an issue open since July.…
Source: DEV Community · Claude
TutorialsOrdinary
The model card said 0.5B. The checkpoint stores 494M. Both are right.
Qwen2.5-0.5B's config declares its vocabulary-by-hidden matrix twice: once as the embedding table,...
Source: DEV Community · Qwen
TutorialsOrdinary
AI agents are your new customers. I built a checker to see which stores they can actually read
A shopper asks ChatGPT for "a waterproof hiking jacket under $150 that ships to Dubai". The answer...
Source: DEV Community · ChatGPT
TutorialsOrdinary
When an AI Agent Says 'Done,' What Exactly Has Finished?
"Done." It's probably the most satisfying word in a coding-agent session. It can also conceal three...
Source: DEV Community