{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/qwen-audio-3-0-tts/","md":"https://postcutoff.com/m/qwen-audio-3-0-tts/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"qwen-audio-3-0-tts","name":"Qwen-Audio-3.0-TTS (Flash / Plus)","org":"Alibaba (Qwen / Tongyi Lab)","family":"Qwen-Audio 3.0","released":"2026-07-20","status":"current","type":"audio/speech","modality_in":["text","audio"],"modality_out":["audio"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_1m_characters":27.59,"unit":"USD per 1M characters for the Plus tier at launch (MarkTechPost). Alibaba cut TTS prices about 70% with the 3.1 generation (2026-09-23), so check current pricing","source":"https://www.marktechpost.com/2026/07/20/alibabas-tongyi-lab-releases-qwen-audio-3-0-tts-a-hosted-text-to-speech-model-in-flash-and-plus-tiers-across-16-languages/"},"price_line":"$27.59 per 1M characters","access":[{"provider":"Alibaba Cloud Model Studio (Singapore / Beijing)","model_id":"qwen-audio-3.0-tts-flash","endpoint":"https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/audio/tts/SpeechSynthesizer","docs":"https://www.alibabacloud.com/help/en/model-studio/qwen-tts"},{"provider":"Alibaba Cloud Model Studio","model_id":"qwen-audio-3.0-tts-plus","docs":"https://www.alibabacloud.com/help/en/model-studio/models"}],"capabilities":[{"name":"#1 on Artificial Analysis TTS arena at launch","detail":"Qwen-Audio-3.0-TTS-Plus ranked first on the Artificial Analysis Text-to-Speech leaderboard in July 2026 (Elo ~1,236-1,237, just ahead of Speechify Simba 3.2 at ~1,234). It was later overtaken (Eleven v4 was #1 by late Sept 2026).","first":false,"discovered":"launch","source":"https://arxiv.org/abs/2607.23938"},{"name":"Controllable, robust multilingual synthesis","detail":"12.5 Hz speech tokenizer plus a five-stage LM + flow-matching training recipe; natural-language instructions and inline tags; 16 languages and 20 Chinese dialect regions; one-pass long-form output up to 3 minutes; voice cloning works from noisy or reverberant references.","first":false,"discovered":"launch","source":"https://arxiv.org/abs/2607.23938"}],"entry":"2026-07-20-qwen-audio-3-0-tts","notes":"Flash tier targets real-time use (~300 ms first packet, press); Plus targets quality (throughput ~16 chars/s, press). Languages: ar, zh, en, fr, de, id, it, ja, ko, ms, pt, ru, es, tl, th, vi. Companion qwen-audio-3.0-realtime-plus/-flash and qwen-audio-3.0-asr-flash also exist. Superseded by Qwen-Audio-3.1 (2026-09-23), but as of 2026-09-29 the Model Studio catalog still lists qwen-audio-3.0-tts-plus as its TTS model, and no 3.1 TTS id is published in the international docs. By 2026-10-25 the 3.1 ids were published (qwen-audio-3.1-tts-plus/-flash, see qwen-audio-3-1-tts-plus); current 3.0 list prices: Plus $0.20 / Flash $0.15 per 10,000 characters (Singapore), per https://www.alibabacloud.com/help/en/model-studio/model-pricing.","verified":"2026-09-29","body_md":"Alibaba's hosted flagship TTS from July 2026.\n\nSources: https://arxiv.org/abs/2607.23938 · https://www.alibabacloud.com/help/en/model-studio/qwen-tts · https://www.alibabacloud.com/help/en/model-studio/models · https://www.marktechpost.com/2026/07/20/alibabas-tongyi-lab-releases-qwen-audio-3-0-tts-a-hosted-text-to-speech-model-in-flash-and-plus-tiers-across-16-languages/","page_url":"https://postcutoff.com/m/qwen-audio-3-0-tts/","standing":{"kind":"speech and audio","newer_count":42,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":null,"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}