NVIDIA Audio Connector for AI agents.
10 live capabilities
Turn spoken audio into text, translated speech, and cloned voices.
Waiting for input…
Why people use NVIDIA Audio
NVIDIA Audio for Professional Transcription and Voice Cloning
With the NVIDIA Audio MCP, your agent does it all in one go. You give it a link, and it cleans, transcribes, and punctuates the audio, handing you a polished document in seconds.
What Vinkius changes
You get professional audio processing without the manual editing.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Multi-language podcast distribution
A podcaster needs to make a 2-hour interview accessible in 5 languages.
- Real-world use case 02
Call center sentiment analysis
A support lead has 100 hours of calls to analyze.
- Real-world use case 03
Consistent brand narration
A creator wants a consistent narrator but doesn't want to hire a voice actor every time.
Complete set · 10capabilities
The complete NVIDIA Audio capability set.
These are the exact actions your AI can choose when you ask it to work with NVIDIA Audio.
01—04
4 capabilities in this set.
Part of 10 available through NVIDIA Audio.
- 01 Capability
List audio models
See which audio models are currently available in the NVIDIA API Catalog.
- 02 Capability
Speaker diarization
Detect and label different speakers within a single audio file.
- 03 Capability
Punctuate text
Fix raw text by adding proper punctuation and capitalization.
- 04 Capability
Classify audio
Identify if a sound is speech, music, or noise with a confidence score.
05—07
3 capabilities in this set.
Part of 10 available through NVIDIA Audio.
- 05 Capability
Clone voice
Create a new voice based on a reference audio sample to generate custom speech.
- 06 Capability
Cancel noise
Strip out background noise from an audio file to get a cleaner recording.
- 07 Capability
Speech to text
Transcribe audio from a public URL into text across multiple languages.
08—10
3 capabilities in this set.
Part of 10 available through NVIDIA Audio.
- 08 Capability
Summarize audio
Turn a long audio transcript into a concise summary of the main points.
- 09 Capability
Text to speech
Convert text into natural sounding speech using various voice parameters.
- 10 Capability
Audio translation
Translate spoken audio directly into a different target language.
Set up in minutes
One URL. Then ask NVIDIA Audio to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use NVIDIA Audio from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it NVIDIA Audio, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable NVIDIA Audio for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the NVIDIA Audio URL.
- Step 03
Save and start
Save the connection and enable NVIDIA Audio in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-audio": {
"url": "https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using NVIDIA Audio
Open Agent mode in chat and ask: "Using NVIDIA Audio, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-audio": {
"url": "https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using NVIDIA Audio
Ask Copilot: "Using NVIDIA Audio, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-audio": {
"url": "https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using NVIDIA Audio
Open Cascade and ask: "Using NVIDIA Audio, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-audio": {
"url": "https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using NVIDIA Audio
Ask Cline: "Using NVIDIA Audio, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add nvidia-audio --transport http "https://edge.vinkius.com/vk_preview_wisSzrtJnZMCHmz1iKrZAGZQEphbj0twPYlJjzMT/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using NVIDIA Audio
Ask Claude: "Using NVIDIA Audio, show me...". 10 tools are ready
Where the request belongs
Work NVIDIA can move forward.
Content creators, transcription service owners, and customer support leads who are drowning in raw audio files and need to turn them into structured data or multi-lingual content quickly.
Podcaster
Creates multi-language content and clones their own voice for automated narrations.
Transcriptionist
Automates the cleanup of messy meeting recordings and separates speakers instantly.
Support Manager
Analyzes call recordings for sentiment and speaker identification to improve team training.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsDeepgram
Transcribe speech to text with blazing speed and accuracy using neural networks trained on real-world audio at scale.
Speechmatics
Automate speech-to-text and text-to-speech. transcribe audio files, generate natural voices, and manage transcription jobs directly.
Cartesia (Voice AI)
Generate lifelike AI voices, clone speech, and transcribe audio with Cartesia's state-of-the-art Sonic models directly from your AI agent.
LMNT (Ultra-low Latency Speech Synthesis)
Synthesize ultra-low latency AI speech, clone voices instantly, and manage your LMNT audio assets directly from any AI agent.
Resemble AI
Generate high-quality AI voices, manage projects, and transform speech with Resemble AI's powerful voice cloning and synthesis capabilities.
Play.ht (Voice Cloning)
Generate ultra-realistic speech and clone voices instantly using Play.ht's advanced AI voice engines directly from your agent.
Bring your own AI
Change the model, client or framework. Keep NVIDIA connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about NVIDIA.
The practical details behind the request, access and result.
How can the NVIDIA Audio MCP help with my podcast?
It helps by automating the boring parts like transcription and noise removal, so you can focus on the content.
Can I use the NVIDIA Audio MCP to clone my own voice?
Yes, you can use it to create a voice clone from a sample to generate new speech that sounds just like you.
Does the NVIDIA Audio MCP support multiple languages?
Yes, it handles translation and transcription for various languages, making it great for global content.
Can the NVIDIA Audio MCP separate different people speaking?
Yes, it uses speaker diarization to identify and label different voices in a single recording.
Is the NVIDIA Audio MCP good for cleaning up noisy audio?
Yes, it includes noise cancellation to make recordings clearer by stripping out background hum and static.
Can I use the NVIDIA Audio MCP to summarize long audio files?
Yes, it can turn long transcripts into short summaries so you can get the main points without listening to the whole thing.
What languages are supported for transcription?
Parakeel models support 50+ languages including English, Portuguese, Spanish, French, German, Mandarin, Japanese, and many more. Specify the language for best results.
Can I clone a specific voice?
Yes! Use the clone_voice capability with a reference audio sample (a few seconds is enough) and the text you want the cloned voice to speak.
What is speaker diarization?
Speaker diarization identifies 'who spoke when' in an audio recording. It segments the audio by speaker and returns timestamps for each speaker's turns.
What audio formats are supported?
The API supports WAV, MP3, FLAC, OGG, and most common audio formats. For best transcription accuracy, use high-quality WAV or FLAC files at 16kHz or higher sample rate.
One connection away
Give your agent a direct line to NVIDIA.
Connect NVIDIA once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available