Use VieNeu inside Claude, ChatGPT and Cursor
No code. Add this address to your AI assistant, sign in with your VieNeu account, and ask it to read in a Vietnamese voice — the audio plays right in the chat.
https://api.vieneu.io/mcpNeeds a VieNeu account with an active token plan — a new account can start a free trial.
Claude
Web, desktop and mobile. Customize → Connectors → Add custom connector, paste the address.
Claude Code
One command, then /mcp to sign in.
claude mcp add --transport http vieneu https://api.vieneu.io/mcpOpenAI API and other apps
The mcp tool in the Responses API, Windsurf, Gemini CLI, Codex CLI, Zed, Goose…
Two ways to use VieNeu
They share a name and a voice catalogue, and nothing else — different install, different billing, different code. Start by picking one.
Cloud API
Send text over HTTPS and get audio back. Nothing to download, no GPU to rent. Billed per submitted character, authenticated with an API key. This is what almost every integration wants.
On-device SDK
A Python package that runs the model locally. No network and no per-character cost; the hardware, the setup and the tuning are yours.
Instant Voice Cloning
Clone any voice with just 3-5 seconds of reference audio. Zero-shot — no fine-tuning needed.
Real-time Streaming
Audio playback starts before the sentence finishes. Under 300ms latency on modern CPUs.
Offline On-device Option
The SDK runs entirely on your hardware — no internet required after the model download. The Cloud API is the hosted alternative.
Multiple Models
From 0.5B (best quality) to Q4 quantized (extreme speed). Pick what fits your hardware.
Vietnamese + English
Native Vietnamese with seamless code-switching to English within the same sentence.
Flexible Backends
PyTorch, GGUF, LMDeploy, Remote API, Intel XPU. One SDK, many deployment options.
Simple Python API
Three lines to generate speech. Supports voice cloning, streaming, batch processing, and more.
from vieneu import Vieneu
tts = Vieneu()
audio = tts.infer(text="Xin chào bạn!")
tts.save(audio, "output.wav")