qwencloud-audio-tts
Turn written text into high-quality spoken audio using QwenCloud's TTS models. Choose between fast standard synthesis (qwen3-tts-flash) or instruction-guided style control (qwen3-tts-instruct-flash), or opt for premium quality via CosyVoice. Select from multiple voices and languages to match your content needs.
qwencloud-audio-tts converts text to natural speech audio using Qwen TTS models via HTTP or WebSocket APIs.
AI-generated summary based on this skill's SKILL.md
Install
QwenCloud/qwencloud-ai/qwencloud-audio-tts · repository language: Python
git clone https://github.com/QwenCloud/qwencloud-ai
cp -r qwencloud-ai/skills/audio/qwencloud-audio-tts ~/.claude/skills/qwencloud-audio-ttsnpx skillfed install QwenCloud/qwencloud-ai/qwencloud-audio-ttsFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What does qwencloud-audio-tts do?
qwencloud-audio-tts converts written text into high-quality spoken audio using QwenCloud's TTS models. You can choose between fast standard synthesis with qwen3-tts-flash, instruction-guided style control with qwen3-tts-instruct-flash, or premium quality via CosyVoice. The skill supports multiple voices and languages to match your content needs.
How can I convert text to audio with qwencloud-audio-tts?
qwencloud-audio-tts provides multiple TTS models for text-to-audio conversion. Use qwen3-tts-flash for fast, standard synthesis, or qwen3-tts-instruct-flash when you need instruction-guided style control over the output. For premium quality audio, CosyVoice is available. Select your preferred voice and language, then submit your text to generate natural speech audio.
Can I generate voiceovers and narration using qwencloud-audio-tts?
Yes, qwencloud-audio-tts is designed for generating voiceovers and audio narration for content. The instruction-guided qwen3-tts-instruct-flash model lets you control speech style, while the standard qwen3-tts-flash model offers fast synthesis. You can select from multiple voices and languages to create professional narration that matches your content.
What TTS voice generation options does qwencloud-audio-tts offer?
qwencloud-audio-tts provides multiple voice and language options across three model tiers. The qwen3-tts-flash model delivers fast, standard voice synthesis. The qwen3-tts-instruct-flash model adds instruction-guided style control for customized speech output. CosyVoice offers premium quality audio. Choose the model and voice that best fits your application's performance and quality requirements.
How do I build or integrate text-to-speech into my application?
qwencloud-audio-tts provides a text-to-speech API for application integration. Select your preferred TTS model—qwen3-tts-flash for speed, qwen3-tts-instruct-flash for style control, or CosyVoice for premium quality—then integrate the API into your application workflow. The skill supports multiple voices and languages, enabling flexible voice narration generation across diverse use cases.
What speech synthesis models are available in qwencloud-audio-tts?
qwencloud-audio-tts offers three speech synthesis options: qwen3-tts-flash for fast, standard audio output; qwen3-tts-instruct-flash for instruction-guided style control over the generated speech; and CosyVoice for premium-quality audio. All models support multiple voices and languages, letting you synthesize natural speech audio tailored to your content and performance needs.
SKILL.md
rendered from the published skill — quoted content, verbatim
> Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code), > see agent-compatibility.md once per session.
Qwen Audio TTS (Text-to-Speech)
Synthesize natural speech from text using Qwen TTS models. This skill is part of qwencloud/qwencloud-ai.
Skill directory
Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.
| Location | Purpose |
|---|---|
scripts/tts.py |
Qwen TTS (HTTP API) — qwen3-tts-flash, |
(truncated - see the full file via the links below)
Read as markdown · JSON record · Browse the source repository
File tree — 11 files
skills/audio/qwencloud-audio-tts/SKILL.md
skills/audio/qwencloud-audio-tts/references/agent-compatibility.md
skills/audio/qwencloud-audio-tts/references/api-guide.md
skills/audio/qwencloud-audio-tts/references/cosyvoice-guide.md
skills/audio/qwencloud-audio-tts/references/execution-guide.md
skills/audio/qwencloud-audio-tts/references/prompt-guide.md
skills/audio/qwencloud-audio-tts/references/sources.md
skills/audio/qwencloud-audio-tts/scripts/gossamer.py
skills/audio/qwencloud-audio-tts/scripts/qwencloud_lib.py
skills/audio/qwencloud-audio-tts/scripts/tts.py
skills/audio/qwencloud-audio-tts/scripts/tts_cosyvoice.py