Barnaby
English · YouTube
AI Voice Glossary
Free to start. No card needed.
Plain-English definitions for TTS, STT, voice cloning, voice design, points, SRT, temperature and MCP — including why there's no pitch control.
Sound tags and written directions work on every plan, Free included. See plans
“It's fast and dead simple to use: paste your text, pick a voice, done. No fuss, no learning curve.”
“As a professor who records frequent online lectures, I’ve found Vocallab AI to be an incredible tool for my workflow. The voice quality is remarkably lifelike…”
Step-by-step guide
How to Use AI Voice Glossary
Start for free — no credit card, no software to install.
Start with TTS and STT
TTS converts text into speech; STT converts speech into a plain transcript — opposite directions, and STT here returns no captions or speaker labels.Understand voice cloning vs voice design
Cloning reuses a real sample of a specific voice with consent; design builds a new voice from a written description, with preview takes before saving it.Learn what a point buys
A point pays for about one second of generated audio, at a slightly different rate in the app than through the public API.Know the two sliders
Speed changes pacing; Temperature changes delivery variation. There is no pitch control — voice character comes from voice choice, not a slider.
AI Voice Glossary
Features & Capabilities
Everything you need to create professional voiceovers — in one tool.
TTS and STT defined
Text-to-speech generates audio from text; speech-to-text returns a plain transcript from audio, with no captions or timings.Cloning vs design defined
Cloning uses a real voice sample with consent; design builds a new voice from a plain-English description.Points and SRT defined
A point pays for roughly one second of audio; SRT is a caption file built from the word-level timing the speech engine returns.Temperature and MCP defined
Temperature controls delivery variation, not pitch — there is no pitch slider. MCP lets an AI assistant use the platform's voice tools directly.Points in the app versus the API
The app spends points at roughly one per 17 characters of text; the public API uses a slightly different, slightly higher rate per character.
Use cases
What Can You Create with AI Voice Glossary?
From TikTok to podcasts — here's where creators use this tool most.
Understanding a confusing term before asking support
Looking up what SRT or MCP actually means before opening a help ticket.Explaining the tool to a non-technical teammate
Sharing plain definitions instead of jargon when introducing the platform to someone new.Deciding which feature actually solves a problem
Realizing 'I want a higher voice' means picking a different voice, not adjusting a pitch slider that doesn't exist.Evaluating whether MCP access is relevant
Understanding what MCP does before deciding whether an assistant-integrated workflow is worth the Pro plan.
vs Standard TTS
VocalLab vs Standard Text-to-Speech
See why creators switch from generic TTS tools to VocalLab.
| VocalLab AI | Standard TTS | |
|---|---|---|
| Audio quality | Studio-quality AI | No |
| MP3 export | Yes | No |
| SRT caption export | Yes | No |
| Word-level highlighting | Yes | No |
| Emotion & style control | Yes | No |
| Commercial rights | Yes | No |
| Instant generation | Yes | No |
| Free tier | No credit card needed | No |
Recommended Voices
Matched to this tool. Play a sample, then use it in Studio.
About this tool
Everything you need to know about AI Voice Glossary
The terms in this space get used loosely, so here's what each one actually means on VocalLab. TTS, text-to-speech, turns written text into spoken audio; STT, speech-to-text, does the reverse, returning a plain transcript with no timings or speaker labels. A point is the unit that pays for generated audio, spent at roughly one per second. SRT is a caption file built from word-level timing. Temperature controls how varied a delivery sounds, not pitch — there's no pitch control at all, only Speed and Temperature. MCP is a way for an AI assistant to use the platform's voice tools directly instead of a person clicking through the app.
People also search for
- ai voice glossary
- what is tts
- what is mcp
- voice cloning vs voice design
- what is a point ai voice
- text to speech terms explained
Is there a pitch control?
No — the two available sliders are Speed and Temperature; pitch isn't adjustable on any voice, so a higher or lower sound comes from picking a different voice.
What does Temperature actually control?
How varied the delivery sounds from one generation to the next — it's not a tone or pitch setting, despite the name sounding like one.
What's the difference between voice cloning and voice design?
Cloning reuses a real person's voice from a short sample with consent; design builds an entirely new voice from a written description, with preview takes before you save one.
What is MCP in this context?
A hosted server that lets an AI assistant call the platform's voice tools directly — listing voices, using a clone, or generating speech — instead of a person doing it through the app.
Turn your script into a voiceover.
60 free points, no card. Paste your text, pick a voice, export the MP3.