DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to serve Breeze TTS 2 speech through the local API with Native Breeze TTS 2 Support for vLLM Omni

Stand up the vLLM-Omni speech endpoint with a Breeze checkpoint and send it a test request.

  • Research
  • Advanced
  • 3 hours
  • From the README
  • Any agent

Authorization notice. Native Breeze TTS 2 Support for vLLM Omni is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Voice cloning. The README says voice cloning is not supported, so use this endpoint only for standard speech and do not try to clone a specific person's voice with it.

Who it is forA developer with a GPU-capable machine and a Breeze TTS 2 checkpoint who wants to test text-to-speech through an HTTP endpoint.

The problemGetting the modified vLLM-Omni source, runtime, and checkpoint to work together needs a setup path that the README points to but does not fully automate.

The outcomeA running speech endpoint at the /v1/audio/speech adapter that returns audio for a text prompt, with the launch configuration checked against the README limits.

What you need first

  • Python 3.10 or newer for the basic checks, and a separate Python 3.12 environment for the model CPU tests
  • Git, to clone the repository and inspect the tag v0.1.0-dev
  • For real inference only: a prepared runtime and a Breeze TTS 2 checkpoint, which the repo does not provide
  • Awareness that Breeze model materials use a research and non-commercial license

Steps

  1. Follow docs/getting-started.md to prepare the runtime and the checkpoint
  2. Install the modified vllm-omni/ source as described in the getting-started guide
  3. Run python examples/speech_client.py --help to see the client options
  4. Send a test request with the client example, following docs/api.md for the /v1/audio/speech adapter

Prompt for your agent

In the repo Sentinel3252/Native-Breeze-TTS-2-Support-for-vLLM-Omni, follow docs/getting-started.md and docs/api.md to start the speech endpoint with a checkpoint at <checkpoint path>. Send one short text prompt through examples/speech_client.py and report whether audio was returned and the server settings used, confirming tensor parallel size 1, eager mode, and prefix caching disabled.

Caveat. The README says the launch configuration still needs runtime validation and that real serving, speech quality, and concurrency have not been verified.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page