[Doc] Update Qwen3-TTS docs for consistency with Omni examples

[linyueqian]

Purpose

Update Qwen3-TTS documentation to be consistent with Qwen2.5-Omni and Qwen3-Omni documentation style, and align with the Speech API documentation in PR #1206.

Changes:

• Add 0.6B model variants to supported models table
• Update default port from 8000 to 8091 for consistency with other examples
• Add 🛠️ Installation section matching Qwen2.5-Omni/Qwen3-Omni style
• Add more supported languages (German, French, Russian, Portuguese, Spanish, Italian)
• Add /v1/audio/voices endpoint documentation
• Use lowercase voice names (vivian, ryan) for consistency
• Add vllm serve command examples with full flags (--trust-remote-code --enforce-eager)
• Add FAQ section (librosa/ffmpeg troubleshooting)
• Add OpenAI SDK and httpx usage examples
• Improve troubleshooting section

Test Plan

Documentation-only change. Verified markdown renders correctly.

Test Result

N/A - Documentation update only.

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
• (Optional) Release notes update. If your change is user facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 0751a5ed83

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[Copilot]

Pull request overview

This PR updates the Qwen3-TTS documentation to align with the documentation style and conventions used in Qwen2.5-Omni and Qwen3-Omni examples. The changes improve consistency across the vLLM-Omni repository and provide better user guidance.

Changes:

• Updated default port from 8000 to 8091 for consistency with other omni examples
• Normalized voice names to lowercase (vivian, ryan) to match API behavior
• Added documentation for 0.6B model variants and additional supported languages
• Added /v1/audio/voices endpoint documentation and usage examples
• Enhanced documentation with OpenAI SDK and httpx code examples

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.

File	Description
examples/online_serving/qwen3_tts/run_server.sh	Updated server port from 8000 to 8091
examples/online_serving/qwen3_tts/openai_speech_client.py	Changed default port to 8091, normalized voice names to lowercase, updated help text
examples/online_serving/qwen3_tts/README.md	Added 0.6B models, vllm serve examples, voices endpoint docs, language list, OpenAI SDK/httpx examples, updated voice names and port references
docs/user_guide/examples/online_serving/qwen3_tts.md	Added Installation section, comprehensive command examples, voices endpoint docs, updated voice names and ports, enhanced troubleshooting

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.