Just in

Local AI · Topic hub

Local Speech & TTS

Whisper transcription and offline voice — Kokoro, Piper, XTTS and Chatterbox on your own machine.

12 articles across guides, comparisons

Bright home studio with a microphone and audio waveform on a laptop, ElevenLabs logo cardGuides

Free AI Voice Generators That Are Actually Free

ElevenLabs' free tier is 10 minutes a month with an attribution catch. The genuinely free routes, hosted and local, mapped side by side with what each bans.

16 Aug5 min read
A dimly lit developer desk at night with a waveform on one monitor showing a long flat silent stretch, and a terminal on the second monitor printing substitution, deletion and insertion counts.Guides

How to Test Whisper Accuracy on Your Own Audio

Stop borrowing WER numbers from LibriSpeech. A 90-minute protocol to build a test set, score it with jiwer, catch hallucinations, and model local-vs-API cost.

14 Aug11 min read
Video editor scrubbing a subtitle timeline in a dark grading suite lit by monitor glow, beneath a large illuminated Descript emblemGuides

AI Captions: The Accuracy Numbers Nobody Publishes

Whisper Large-v3 sits near 4.2% word error rate on clean audio. Dirty audio drops tools to 70-85%. The fix is upstream of whichever tool you picked.

14 Aug5 min read
Cinematic local AI hardware illustration for: XTTS Voice Cloning Locally: Clone Any Voice, Fully OfflineGuides

XTTS Voice Cloning Locally: Clone Any Voice, Fully Offline

XTTS clones a voice from a 6-second sample on your own GPU, fully offline. The 2026 install, real VRAM numbers, and where narration quality breaks down.

27 Jul5 min read
Cinematic local AI hardware illustration for: Voxtral: Mistral's Offline Transcription Model, TestedGuides

Voxtral: Mistral's Offline Transcription Model, Tested

Mistral's Voxtral runs speech-to-text fully offline under Apache 2.0, in 3B and 24B sizes. VRAM needs, how it differs from Whisper, and the browser build.

27 Jul4 min read
Cinematic local AI hardware illustration for: Run Whisper Locally: Free Offline Transcription (2026)Guides

Run Whisper Locally: Free Offline Transcription (2026)

faster-whisper install to first transcript, the large-v3-vs-turbo call I make, and what a real file costs on a GPU versus a CPU, with no API bill involved.

27 Jul5 min read
Cinematic local AI hardware illustration for: Piper TTS: Fast Offline Voice Synthesis on a Raspberry PiGuides

Piper TTS: Fast Offline Voice Synthesis on a Raspberry Pi

Piper runs real-time neural text-to-speech on a Raspberry Pi with no GPU. The install, the license change nobody mentions, and which tier fits a Pi 4 vs a Pi 5.

27 Jul5 min read
Cinematic local AI hardware illustration for: Local Voice AI: Whisper, TTS & Offline Assistants (2026)Guides

Local Voice AI: Whisper, TTS & Offline Assistants (2026)

The self-hosted voice stack map: Whisper/faster-whisper for speech-to-text, Kokoro/Piper/Chatterbox/XTTS for voices, Ollama for the brain — wired offline.

27 Jul7 min read
Cinematic local AI hardware illustration for: Kokoro TTS Locally: The 82M-Parameter Voice Model SetupGuides

Kokoro TTS Locally: The 82M-Parameter Voice Model Setup

Why a tiny Apache-2.0 model with no voice cloning is still the narration tool I install first, plus the actual pip-install-to-first-spoken-line steps.

27 Jul5 min read
Cinematic local AI hardware illustration for: Build a Fully Offline Voice Assistant With Home AssistantGuides

Build a Fully Offline Voice Assistant With Home Assistant

Faster-whisper, Piper, and Ollama wired into Home Assistant Assist, with real latency numbers for built-in intents, GPU tier and CPU-only Raspberry Pi hardware.

27 Jul5 min read

More in Local AI