Alibaba’s Tongyi Lab Releases Qwen-Audio-3.0-TTS, a Hosted Text-to-Speech Model in Flash and Plus Tiers Across 16 Languages

Alibaba’s Tongyi Lab has released Qwen-Audio-3.0-TTS , a production-oriented text-to-speech (TTS) system. The model ships in two variants from the same lineage. Flash targets real-time interaction. Plus targets high-quality generation. Both are delivered as hosted models through Alibaba Cloud Model Studio , not as downloadable weights.

The release focuses on four things developers hit in production: broader language coverage, natural-language style control, fine-grained tag control, and robustness when the reference audio is not clean. Qwen-Audio-3.0-TTS-Plus also ranks first on the independent Artificial Analysis Text-to-Speech leaderboard.

The two tiers map to different jobs. Flash is tuned for real-time interaction, with first-packet latency at the 300 ms level. Plus is tuned for high-quality generation, where naturalness and timbre fidelity matter more than speed.

The model IDs are qwen-audio-3.0-tts-flash and qwen-audio-3.0-tts-plus . Both are called over a bidirectional WebSocket streaming protocol. The API supports PCM, WAV, MP3, and Opus, with sample-rate output up to 48 kHz. It exposes streaming input and output, voice cloning, Voice Design , and instruction control. Alibaba provides the DashScope SDK plus raw WebSocket examples in Python, Java, Go, C#, PHP, and Node.js, across its Singapore and Beijing regions.

The model also handles one-pass long-form synthesis up to 3 minutes, hard text-normalization cases, and vocoder super-resolution for 48 kHz output.

Qwen-Audio-3.0-TTS supports 16 languages : Arabic, Chinese, English, French, German, Indonesian, Italian, Japanese, Korean, Malay, Portuguese, Russian, Spanish, Tagalog, Thai, and Vietnamese. Seven of these are newly added versus the prior line. It also covers 20 Chinese dialect regions.

On multilingual intelligibility, the model family posts the best word/character error rate (WER/CER) in 10 of the 16 languages. Flash delivers the lowest average WER/CER at 3.87 ; Plus is close at 3.96 . Lower is better on this metric.

On speaker similarity, Plus ranks first across all 16 languages with an average of 82.75 , and Flash follows at 80.44 . The release also adds a curated preset voice library spanning the 16 supported languages, so teams can ship a voice without cloning one first.

For precise control, the research team embed inline tags directly in the target text. The release adds 86 fine-grained inline tags for localized control at the phrase and word level. These cover expressive transitions and non-verbal events such as laughter, breathing, coughing, and sighing.