Works with the AI Agents you already use
Qwen Voice MCP
Turn text to speech and clone voices using Qwen TTS and CosyVoice models via MCP.
Free
Qwen Voice MCP
Example session with this skill installed
Convert this text into a speech file using an mp3 format: 'Welcome to the project demonstration.'
- Read your context and instructions
- Compiled the qwen voice mcp
I have generated the audio file for your text using the default Qwen Voice model.
Speech Synthesis Result
| Attribute | Value |
|---|---|
| Audio Path | /tmp/outputs/speech_20231027_1015.mp3 |
| Format | mp3 |
| Duration | 2.4 seconds |
| Characters | 35 |
| Model | qwen-tts-v1 |
| Estimated Cost | ¥0.007 |
Next steps
- Access the file at the path provided above to listen to the output.
- If you need a different tone, I can list available preset voices for this model.
- Provide a 5-60s audio clip if you would like to clone a specific voice for this text.
Connects securely to your tools. The creator never sees your data.
About this skill
Integrating high-quality text-to-speech and voice cloning into your agent workflows usually requires managing complex API state, credit balances, and model IDs. This skill provides a direct interface to Qwen Voice models via MCP, handling synthesis and voice replication without the configuration overhead.
What it does
- Speech synthesis converts text to audio files in mp3, wav, pcm, or opus formats using Qwen TTS and Sambert models.
- Voice cloning replicates a target voice from a 5 to 60 second reference recording to create a reusable voice ID.
- Model discovery retrieves live lists of available voice models, capabilities, and real-time pricing.
- Balance management monitors account credits and provides recharge links when thresholds are hit to prevent failed synthesis jobs.
How it works
- Identify the goal by determining if the user needs standard synthesis, a voice clone, or a balance check.
- Select the model using the
list_voice_modelstool or defaulting to the verified server standard. - Execute the task by writing the tool call to a JSON file and running it through the MCP executor.
- Deliver the artifact by returning the local path to the generated audio file or the new voice ID for future use.
Frameworks & tools
This skill interfaces with DashScope/Qwen TTS, CosyVoice, and Sambert models. It runs through the mcp-to-skill executor using Node.js.
Why this beats prompting it yourself
Manual prompting often leads to hallucinated model names or failed calls due to unmonitored API balances. This skill includes pre-call balance verification and dynamic model discovery to ensure every request is valid and funded before execution.
Use cases
- Generate narration for content scripts or automated video dubbing.
- Clone brand voices from short audio samples for consistent customer interactions.
- Check API status and remaining credits before starting large batch synthesis jobs.
- Format conversion of text blocks into specific audio codecs like opus or pcm.
Known limitations
Does not support speech-to-text, music generation, or sound effects. Reference audio for cloning must be under 20MB and between 5 and 60 seconds long.
No speech-to-text or music generation. Reference audio for cloning must be 5-60 seconds and under 20MB. Requires Node.js for the MCP executor.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts