DEDUPED Hot AI repos, turned into use cases Get the Monday 5
188 stars · Python

How to use Nari Qwen3 TTS: what you can do with it

What is Nari Qwen3 TTS? Nari Qwen3-TTS is a Python serving implementation of the Qwen3-TTS 1.7B CustomVoice model that exposes HTTP and WebSocket speech generation on a single NVIDIA H100.

How do I use it? Confirm the host has an NVIDIA H100, the NVIDIA Container Toolkit, and a CUDA 13.0 compatible driver; then run docker run --rm --gpus all -p 8000:8000 -e HF_TOKEN -e QWEN3_TTS_PROFILE=ttfa -v nari-qwen3-tts-cache:/home/nari/.cache ghcr.io/nari-labs/nari-qwen3-tts:latest; wait for model loading and CUDA Graph capture to finish, then run curl --fail http://127.0.0.1:8000/ready. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Self-host a speech API on an H100 with Docker

    Run the published container on an H100 and expose an OpenAI-shaped speech endpoint on port 8000.

    View prompt
    In the nari-labs/nari-qwen3-tts repo, start the Docker container on this H100 host using the README run command, then poll `http://127.0.0.1:8000/ready` until it succeeds. Expected output: a ready response and a WAV file from a test request to `/v1/audio/speech`. Verify that the readiness check returns success only after the warm-up request has completed.

  • Turn a script into a WAV narration file

    Send text to the speech endpoint with curl and save the returned audio as speech.wav.

    View prompt
    In the nari-labs/nari-qwen3-tts repo, send the text in <script-file> to the local `/v1/audio/speech` endpoint with response_format set to wav and save the result as speech.wav. Expected output: a playable WAV file that matches the script. Verify that the file exists and that the request used speed 1.0, since the README says that is the only supported speed.

  • Speak live text as it arrives over WebSocket

    Stream incremental text to the WebSocket speech endpoint so audio starts before the full sentence exists.

    View prompt
    In the nari-labs/nari-qwen3-tts repo, read docs/websocket.md and write a client that connects to ws://127.0.0.1:8000/v1/audio/speech/ws and sends the text from <text-source> in increments. Expected output: audio chunks received while text is still being sent. Verify that the client handles the protocol described in the docs without guessing message formats.

  • Choose a latency or throughput profile for load

    Switch between ttfa, balanced, and throughput profiles to match a latency target or a request volume.

    View prompt
    In the nari-labs/nari-qwen3-tts repo, start the server with the <profile> profile (ttfa, balanced, or throughput) and send a fixed set of test requests to `/v1/audio/speech`. Expected output: a short table of time to first audio and completed requests for each profile tested. Verify that each run started only after `/ready` returned success.

Quick start with Nari Qwen3 TTS

  1. Check you have what it needs: A Linux x86_64 host with an NVIDIA H100 GPU; NVIDIA Container Toolkit and a driver compatible with CUDA 13.0 (for Docker); Docker, or uv with Python and the system packages build-essential, libsndfile1, and sox.
  2. Open nari-labs/nari-qwen3-tts on GitHub and read the README and license.
  3. Confirm the host has an NVIDIA H100, the NVIDIA Container Toolkit, and a CUDA 13.0 compatible driver.
  4. Run docker run --rm --gpus all -p 8000:8000 -e HF_TOKEN -e QWEN3_TTS_PROFILE=ttfa -v nari-qwen3-tts-cache:/home/nari/.cache ghcr.io/nari-labs/nari-qwen3-tts:latest (inferred, check the README)
  5. Wait for model loading and CUDA Graph capture to finish, then run curl --fail http://127.0.0.1:8000/ready
  6. Send a test request to http://127.0.0.1:8000/v1/audio/speech with model set to Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice and a short input.

These steps come from our top use case, Self-host a speech API on an H100 with Docker, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for nari-labs/nari-qwen3-tts

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Nari Qwen3 TTS alternatives · Best AI repos for Software and DevOps

About this repo

Requirements

  • A Linux x86_64 host with an NVIDIA H100 GPU
  • NVIDIA Container Toolkit and a driver compatible with CUDA 13.0 (for Docker)
  • Docker, or uv with Python and the system packages build-essential, libsndfile1, and sox
  • A Hugging Face token (HF_TOKEN) if the model files need to be downloaded

Add this badge to your README

Maintain Nari Qwen3 TTS? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/nari-labs/nari-qwen3-tts.svg)](https://dedupedai.com/use-cases/nari-labs-nari-qwen3-tts/?utm_source=github&utm_medium=badge&utm_campaign=nari-labs-nari-qwen3-tts)

HTML 

<a href="https://dedupedai.com/use-cases/nari-labs-nari-qwen3-tts/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=nari-labs-nari-qwen3-tts"><img src="https://dedupedai.com/badge/nari-labs/nari-qwen3-tts.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Nari Qwen3 TTS

What is Nari Qwen3 TTS?

Nari Qwen3-TTS is a Python serving implementation of the Qwen3-TTS 1.7B CustomVoice model that exposes HTTP and WebSocket speech generation on a single NVIDIA H100. It is an open-source project on GitHub: https://github.com/nari-labs/nari-qwen3-tts.

How do I use Nari Qwen3 TTS?

Confirm the host has an NVIDIA H100, the NVIDIA Container Toolkit, and a CUDA 13.0 compatible driver; then run docker run --rm --gpus all -p 8000:8000 -e HF_TOKEN -e QWEN3_TTS_PROFILE=ttfa -v nari-qwen3-tts-cache:/home/nari/.cache ghcr.io/nari-labs/nari-qwen3-tts:latest; wait for model loading and CUDA Graph capture to finish, then run curl --fail http://127.0.0.1:8000/ready. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Nari Qwen3 TTS for?

Developers and platform engineers who need a self-hosted text-to-speech endpoint on an H100 GPU host.

What can I do with Nari Qwen3 TTS?

4 use cases so far, for example: Self-host a speech API on an H100 with Docker; Turn a script into a WAV narration file; Speak live text as it arrives over WebSocket. Each has steps and a copy-paste agent prompt.

What do I need to run Nari Qwen3 TTS?

A Linux x86_64 host with an NVIDIA H100 GPU; NVIDIA Container Toolkit and a driver compatible with CUDA 13.0 (for Docker); Docker, or uv with Python and the system packages build-essential, libsndfile1, and sox; A Hugging Face token (HF_TOKEN) if the model files need to be downloaded.

What are alternatives to Nari Qwen3 TTS?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Nari Qwen3 TTS safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.