Verbatik AI
OpenClaw Skill

Give Your OpenClaw Agent a Voice

Turn your OpenClaw into an autonomous voice studio. Generate speech in 2,700+ voices, clone any voice from a 10-second sample, and produce audio in 50+ languages — all from one chat message.

Install Skill — Free to Set UpView on ClawHub

Works on Telegram, Discord, or any chat platform via OpenClaw

Read this blog post aloud in a warm female voice.
🦞Done. Generated 2 minutes of audio using the “Jenny” voice in English. Here's your shareable URL — stream it, download it, or embed it anywhere.

Setup in 3 Steps

From zero to voice-enabled agent in under a minute

🔑

1

Get Your API Key
Sign up at api.verbatik.com, grab your API key (starts with vbt_), and you're ready to go.

⚡

2

Install the Skill
Run one command to add the Verbatik skill to your OpenClaw agent.
openclaw skill add verbatik/text-to-speech-and-voice-cloning-agent

🚀

3

Give It Your Key
Add your Verbatik API key to your OpenClaw workspace and let your agent generate speech, clone voices, and produce audio autonomously.

Just tell your agent what to do

No dashboards. No file uploads. No switching apps. Just a conversation with your OpenClaw agent.

Generate a voiceover for this product description in a professional male voice.YOU
🦞Done. Generated 45 seconds of audio using the "Marcus" voice. Here's your URL — ready to embed in your landing page.
Clone my voice from this audio file and read my newsletter intro with it.YOU
🦞Voice cloned successfully (99.1% similarity). Generated your newsletter intro — 1 minute 12 seconds. Shareable link ready.
How much would it cost to generate audio for a 5,000-word blog post?YOU
🦞~25,000 characters. With a pre-trained voice that's $0.05. With your cloned voice, $2.50. Your current balance is $12.40 — plenty for either option.
Translate this script to Spanish and Japanese, then generate audio for each with a native female voice.YOU
🦞Translated and generated. Spanish audio: 2m 15s using "Sofia". Japanese audio: 2m 08s using "Yuki". Both URLs are ready.

What your agent can do with Verbatik

2,700+ Pre-trained Voices
Browse and generate speech with neural voices across 50+ languages. Filter by language, gender, or name. SSML support included.
Instant Voice Cloning
Clone any voice from a 10-second audio sample. Your agent handles the upload, cloning, and generation in one conversation.
Emotion & Style Control
7 emotions, adjustable speed (0.5x–2x), pitch (-12 to +12 semitones), volume, and natural interjections like (laughs) and (sighs).
Cost-Aware Generation
Your agent checks your balance and estimates costs before generating. No surprise bills. No failed jobs halfway through.
Multilingual Production
Generate audio in 50+ languages with native voices. Your agent can translate and produce voiceovers in multiple languages from a single prompt.
Voice Library Management
List, preview, and manage your cloned voices. Your agent can audit your library, delete unused clones, and generate previews.
Pay-as-you-go

Simple, Transparent Pricing

The skill is free. You only pay for the audio you generate through Verbatik's prepaid balance.

  • The OpenClaw skill itself is free — just install and connect
  • Same prepaid balance as the REST API and MCP
  • Your agent can check your balance before generating
  • No subscriptions. No monthly fees. Pay for what you generate

What

Cost

Pre-trained voice TTS

$0.002 per 1,000 characters

Cloned voice TTS

$0.10 per 1,000 characters

Voice cloning

$3.00 per clone

Browsing voices, checking balance, estimating costs

Free

Testimonials

Loved by creators worldwide

Trustpilot

Craig P.

GB

“I was really surprised at just how good some of the voices are. You can add tags for emphasis, pauses, and pronunciation. Great for video voice-overs. Recent additions also allow AI photos, videos, and music.”

G2

Cristian C.

Administrador

“VERBATIK is straightforward to use and improves content quality quickly. I value its ability to provide suggestions and corrections while keeping my intended tone intact.”

Trustpilot

Bejan Andrei

MD

“We use Verbatik for promotional videos, explainers, and short ads. The AI voices sound professional, avatars look great, and the video generator helps produce content fast.”

Capterra

Tom G.

Mr

“I like the way text to speech is working, very fast, especially when using with API's and very good voice cloning ability.”

GetApp

Makgotso R.

Content Creator

“The broad range of AI voices and the ability to personalize the voice experience is very valuable to me as a content creator.”

Trustpilot

Lucian

RO

“The voices sound incredibly natural after recent updates. You can clone your voice, generate AI avatars, or mix in background music — all from the same dashboard.”

Ready to connect

Ready to let your agent speak?

Get your API key and connect your OpenClaw to Verbatik. Manage your voice content by chatting with your agent on Telegram, Discord, or any chat platform.

Get Your API KeyView on ClawHub
Free skillNo subscriptionPay only for what you generate

Not using OpenClaw? Use Verbatik from any AI via MCP. Use responsibly — you are responsible for all content generated through your account.