Skip to content
Agentmart
Submit a tool

xsai-audio

Generate or stream speech and transcribe recordings with xsAI's audio package.

Skill by moeru-ai

IndexedMIT★ 664
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/moeru-ai-xsai-audio

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate or stream speech and transcribe recordings with xsAI's audio package.

Use cases: audio-video

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/xsai-audio

What's inside

Skill name
xsai-audio
Description
Generate or stream speech and transcribe recordings with xsAI's audio package.
License
MIT
Instructions
13 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# xsAI audio

Read https://xsai.js.org/audio.md. Make sure that the API matches the installed xsAI version.

- Use `@xsai/audio` or the existing `xsai` package with the project's endpoint, model, and voice configuration.
- Create a model with `speech()`, `transcriptions()`, or `transcriptionsNonStreaming()`. Operations take the model first: `generateSpeech(model, { input, voice })`, `generateTranscription(model, { audio })`.
- If the service does not support server-sent events (SSE), use `transcriptionsNonStreaming()`.
- `streamSpeech` returns a `Response`. `generateSpeech` reads its body into a `Blob`.
- For HTTP and network failures, read https://xsai.js.org/shared.md.

For code changes, make sure that the installed types accept the code. Test the affected behavior with existing tests or mock responses.

From moeru-ai/xsai, MIT.

More from moeru-ai/xsai

Compare and alternatives

    Featured in

    Signals

    Stars
    664
    Forks
    62
    Open issues
    4
    Last commit (this folder)
    Oct 10, 2026 (17 days ago)
    Last release
    Sep 30, 2026 (27 days ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    License
    MIT
    Repository
    github.com/moeru-ai/xsai
    Website
    xsai.js.org
    First seen
    Oct 24, 2026
    Last checked
    Oct 24, 2026
    Source
    GitHubgithub-graphql

    More from moeru-ai

    Cite this page

    xsai-audio skill. Agent Mart. https://agentmart.dev/skills/moeru-ai-xsai-audio (last updated 2026-10-24)