qwen3-tts

qwen3-tts is a skill for Claude Code, Codex from calesthio/generative-media-skills. It costs 110 tokens per session (5,439 once invoked), scanned A, original, MIT.

A guide to Qwen3-TTS, Alibaba and Qwen’s multilingual text-to-speech models for turning text into spoken audio. It covers hosted cloud routes and open-weight models, including realtime speech, voice cloning, voice design, and delivery controls.

In plain words
What is it for?
Use it to build narration, e-learning, audiobooks, interactive speech, multilingual audio, voice cloning, or custom voice design with Qwen3-TTS.
Why use it?
It helps developers choose between hosted and self-managed speech generation and between realtime and non-realtime output. It also clarifies which model, language, voice, region, and usage limits need checking before deployment.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to build narration, e-learning, audiobooks, interactive speech, multilingual audio, voice cloning, or custom voice design with Qwen3-TTS.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/calesthio/generative-media-skills/qwen3-tts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add calesthio/generative-media-skills --skill qwen3-tts
Clone the repo
git clone --depth 1 https://github.com/calesthio/generative-media-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qwen3-tts

README.md
[![agentmods](https://agentmods.dev/badge/skills/calesthio/generative-media-skills/qwen3-tts/github.svg)](https://agentmods.dev/skills/calesthio/generative-media-skills/qwen3-tts)
Your own site
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/qwen3-tts"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/qwen3-tts/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for qwen3-tts

Your own site · 80×15
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/qwen3-tts"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/qwen3-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 64
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Excessive Agency · line 158
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 182
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.05439
Opus 5 $0.00055 $0.02720
Sonnet 5 $0.00022 $0.01088
Haiku 4.5 $0.00011 $0.00544

Measured 9d ago against content hash e99b8ee47491, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qwen3-tts scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation" \
skills/providers/text-to-speech/qwen3-tts/SKILL.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qwen3-TTS production guidance

Use this skill to plan, invoke, review, and document Qwen3-TTS speech generation. Treat every model ID, price, region, quota, voice list, and limit below as volatile; the facts marked "verified 2026-07-10" were checked against official Alibaba/Qwen sources on that date.

What Qwen3-TTS is, and which boundary matters

Documented facts:

  • Qwen3-TTS is Alibaba/Qwen's multilingual text-to-speech model family for expressive, controllable, streaming-capable speech generation, with hosted DashScope/Model Studio routes and open-weight research/deployment checkpoints. Qwen's technical report describes 12Hz and 25Hz model variants, 0.6B and 1.7B sizes, voice cloning, voice design, multilingual generation, streaming, and Apache-2.0 model/tokenizer release intent. Source: https://arxiv.org/html/2601.15621v1 and https://github.com/QwenLM/Qwen3-TTS (verified 2026-07-10).
  • Alibaba Cloud Model Studio exposes Qwen-TTS/Qwen3-TTS via HTTP/SSE non-real-time synthesis and WebSocket real-time synthesis. The non-real-time user guide says it is suited to latency-tolerant audiobook, e-learning, and content-production work, while real-time synthesis is designed for low-latency assistants, audiobook streaming, and customer service. Sources: https://help.aliyun.com/en/model-studio/non-realtime-tts-user-guide and https://help.aliyun.com/zh/model-studio/realtime-tts-user-guide (verified 2026-07-10).
  • Hosted Qwen3-TTS is not one universal endpoint. It has different model families for built-in voices, instruction control, voice design, voice cloning, and realtime variants. Verify the chosen region and model list immediately before production. Source: https://help.aliyun.com/en/model-studio/non-realtime-tts-user-guide (verified 2026-07-10).

Production heuristic:

  • Use hosted DashScope when you need managed infrastructure, built-in voices, quick custom voice creation, or production traceability. Use open weights only when you have GPU capacity, need local/private inference, need to inspect or adapt model behavior, or cannot send script/audio data to a hosted provider.

Read the full file on GitHub · 256 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 256 lines · 110 tokens per session scan A e99b8ee47491

Subscribe to this mod's changes

qwen3-tts is a skill published in the GitHub repository calesthio/generative-media-skills (171 stars, last pushed 2mo ago), licensed MIT. It adds 110 tokens to every session and 5,439 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

cliptalk-caption-layout-director

Lays out subtitles for an existing ClipTalk timeline, including top/bottom placement, safe margins, readable wrapping, bilingual order, and review rendering.

GML-MMGroup/ClipTalk · 37 tokens

video-translate

Translate and dub existing videos into multiple languages using HeyGen. Use when: (1) Translating a video into another language, (2) Dubbing video content with lip-sync, (3) Creating multi-language versions of existing videos, (4) Audio-only translation without lip-sync, (5) Working with HeyGen's /v2/videotranslate…

calesthio/OpenMontage · 77 tokens

translation

A translation tool for converting current text, conversations, or explicitly provided files into a target language while preserving their meaning and key information.

limecloud/lime · 29 tokens

Stable Diffusion

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

agentic-in/elephant-agent · 47 tokens

cliptalk-cover-director

Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.

GML-MMGroup/ClipTalk · 53 tokens

cliptalk-smart-reframe

Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.

GML-MMGroup/ClipTalk · 58 tokens