- AUDIO
- CLONES
- SCRIPTS
- HUMAN
Short answer
How can I turn text into speech with my AI?
Your AI uses NVIDIA Audio to convert text into spoken audio using a library of natural voices or by cloning a specific voice. You'll get finished audio files ready for your projects.
The results of your request
What you get from your AI
Depending on what you ask, your AI produces one of these outcomes.
AUDIO
Spoken audio files
The AI processes your text and provides a playable audio file using the selected voice.
CLONES
Custom voice models
You get a digital version of a specific voice that the AI can use for future scripts.
SCRIPTS
Text-to-speech ready
Your written content is mapped to vocal patterns to ensure the pacing sounds natural.
HUMAN
Manual review needed
You'll need to listen to the output to check for correct emphasis or emotional tone.
The workflow
What your AI does when the script arrives.
The AI handles the heavy lifting of vocal synthesis and voice modeling.
Voice selection
The AI picks a voice from the available library or prepares to use a custom one.
clone_voiceAudio synthesis
The AI converts your written words into a continuous audio stream.
text_to_speechVoice cloning
The AI analyzes a sample to create a unique vocal profile for your use.
clone_voiceFinal rendering
The AI finishes the audio file so it is ready for playback or download.
text_to_speech
Try it
Copy these to start.
Use these prompts to trigger the audio tools immediately.
Starting points
Replace the bracketed text with your actual script or voice sample details.
NVIDIA Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — NVIDIA capabilities are ready to use.
{
"mcpServers": {
"nvidia-audio-mcp": {
"url": "https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp"
}
}
}Convert this script into audio using a natural male voice: [paste script]
Clone this voice from the provided audio sample: [upload/link sample]
Read this paragraph using the custom voice we just cloned: [paste text]
Generate a voiceover for this short story using a calm, female voice: [paste story]
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect NVIDIA Audio once, then ask.
Just follow the link to connect the MCP. Your login stays encrypted, and you can start prompting your AI client right away.
Connect NVIDIA Audio to your AIFAQ
Common questions
- 01
Can the AI edit the audio file after it is generated?
No. The AI generates the audio from text, but it does not have tools to edit waveform data or perform post-production.
- 02
Can I use any voice I want?
You can use the built-in natural voices or create your own using the cloning tool.
- 03
Does the AI handle the script writing too?
The AI can write scripts if you ask, but the specific audio tools only act on the text you provide.
- 04
Can the AI change the background music in the audio?
No. The tools are strictly for text-to-speech and voice cloning.
- 05
How do I get the audio file?
Once the AI finishes the process, it provides the audio output for you to use.
More questions about NVIDIA Audio? The Connector page answers them. See everything the NVIDIA Audio Connector can do
Connect NVIDIA to Claude, Cursor, ChatGPT & more
