Skip to content
explainroo

Guides · 28 articles

Voice, captions and sound

Narration with real or synthetic voices, open text-to-speech models, word timing with Whisper, caption formats, and getting music and voice to sit well together.

AI Voice-Over for Videos: How to Get Natural Narration

AI voice-over uses text-to-speech software to turn a written script into spoken audio. A lifelike voice helps, but natural narration also depends on clear…

3 min read

Text-to-Speech for Videos: How to Choose a Voice Engine

When you make a narrated video, a text-to-speech voice engine turns your written script into spoken audio.

4 min read

Kokoro TTS: A Practical Guide to the Open Voice Model

If you need spoken narration for a project, Kokoro is an open-weight text-to-speech (TTS) model, software that turns written text into audio.

4 min read

Kokoro TTS Voices: The List and How to Pick One

When you use Kokoro to turn text into speech, your voice choice shapes how the narration sounds and whether it fits your audience.

3 min read

Best Open Source Text-to-Speech Models: Kokoro, Piper, Chatterbox and More

For narration, accessibility, or product use, open text-to-speech (TTS) models let you generate speech without depending entirely on a commercial service.

3 min read

Offline Text-to-Speech: Running a Voice Model on Your Own Computer

Offline text-to-speech (TTS) lets your computer read text aloud without sending it to a speech service. The voice model turns words into audio on your computer.

4 min read

How to Write a Voice-Over Script

A voice-over script contains the words a narrator speaks in a video or audio production. For video, it also needs to fit what viewers see and hear, such as…

4 min read

Speaking Rate: How Many Words per Minute for Voice-Over and Video

For general English voice-over, start at about 150 words per minute (WPM). Plan for 140–160 WPM. Adjust that range to the script and audience, then account…

3 min read

Word-Level Timestamps with Whisper

For captions or visuals that follow each spoken word, sentence-level transcript timing is too broad.

3 min read

faster-whisper: Fast Local Transcription with Word Timestamps

For local transcription, faster-whisper runs OpenAI’s Whisper speech-recognition model on your computer and can return word-level timestamps.

3 min read

Forced Alignment: Matching Audio and Text Word by Word

Forced alignment is the process of matching the supplied text to the audio and assigning times to its words.

3 min read

How to Add Captions to a Video

If you already have camera footage, use your video host’s caption-upload or editing feature instead: explainroo does not edit existing footage.

2 min read

Closed Captions vs. Subtitles: What's the Difference?

Closed captions show spoken words and meaningful sounds for viewers who are deaf or hard of hearing. Subtitles show dialogue, often in another language.

3 min read

Open Captions: What They Are and When to Burn Them In

When you publish a video, you can place captions directly on the image or add a separate caption track viewers can turn on or off.

3 min read

SRT Files: What They Are and How to Make One

When you need subtitles for a video, an SRT file gives a player the caption text and the times each caption should appear.

3 min read

WebVTT vs. SRT: Which Caption Format to Use

When you add captions to an online video, use the format your video player accepts. WebVTT supports caption positioning and styling in compatible web players.

3 min read

Word-by-Word Animated Captions: How They Work

In a video with word-by-word animated captions, each spoken word lights up or changes style as the voice reaches it.

3 min read

Audio Ducking: Lowering Music Under a Voice-Over

When narration and background music play at the same time, the music makes speech harder to understand.

3 min read

LUFS for YouTube and Social Video: Loudness Targets Explained

For a narrated video, make sure the voice stays clear whether viewers listen on a phone or laptop, or through headphones, without startling them or getting…

4 min read

How to Sync Animation to Narration Word by Word

An explainer animation is easier to follow when each visual change appears on the word that introduces it.

4 min read

How to Fix Kokoro TTS Pronunciation of Names, Acronyms and URLs

When Kokoro text-to-speech reads a script aloud, it sometimes misreads names, turns an acronym into a word, or speaks a web address as a string of symbols.

3 min read

How to Do a Voice-Over and Add It to Your Video

A voice-over is narration recorded separately from the picture and placed over video. You can record your own voice, generate narration, or record directly…

4 min read

A Free ElevenLabs Alternative for Video Narration: Local Voices with explainroo

For explainer videos and product demos, explainroo generates English narration and builds the video on your computer.

4 min read

How to Make Subtitles with Whisper (SRT and VTT)

Save the timed captions as an SRT or VTT file. SRT works with many video players and editors; VTT is commonly used in web video.

3 min read

kokoro-js: Running Kokoro Text-to-Speech in Node.js

js, use kokoro-js, a JavaScript interface to Kokoro, an open-weight text-to-speech model. Text-to-speech, or TTS, means generating spoken audio from written…

3 min read

Whisper Alternatives for Transcription and Word Timing

Choose a speech-to-text service by the timestamp detail you need. Some services timestamp segments; others mark the start and end of each word.

4 min read

ElevenLabs vs. Kokoro TTS for Video Narration

For video narration, ElevenLabs generates voices through a hosted service. ElevenLabs suits creators who want a managed service and built-in narration tools.

4 min read

How to Make a Video Transcript

A video transcript is a readable text version of a video's content. It includes spoken words and, when needed, sounds and visual details that help explain…

3 min read

Videos made with explainroo

A coding agent made each of these with explainroo, from the script to the finished MP4.

Free and open source

Make your own with your AI agent

explainroo lets a coding agent like Claude Code or Codex make narrated explainer videos and product demos. The voice, the word timing and the rendering run on your own computer, with no API key and no cost per video.

Copy this into your AI agent

Make me a short explainer video about [your topic]. Use explainroo for it: clone https://github.com/vincentsch/explainroo, read its AGENTS.md and follow the steps.

Getting started Example videos GitHub

Made with explainroo: How compound interest works