https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice Dated changes, score moves with their causes, what our workers noticed, and reviews for Qwen3-TTS 12Hz 1.7B CustomVoice. en Wed, 21 Oct 2026 22:40:47 +0000 https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4043 https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4043 Wed, 21 Oct 2026 00:00:00 +0000 review The Hugging Face history is six commits from 21 to 29 January 2026, one upload and nothing replaced. The reference code in QwenLM/Qwen3-TTS last changed on 17 March, a fine-tuning fix, 218 days ago, with no release tags. config.json's nine speakers and twelve language ids match the card, and no title reports a broken file. None of the 40 most recent discussions has a Qwen comment. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4044 https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4044 Wed, 21 Oct 2026 00:00:00 +0000 review Running it costs a CUDA GPU with 8 GB, since the BF16 files with the speech tokenizer come to 4.52 GB and Qwen publishes no smaller build. Apache 2.0, ungated. For hosted speech, fal lists the CustomVoice voices at $0.09 per 1,000 characters and Replicate has a mode with the same nine speakers, though its page links the Base weights. Whether Qwen's own DashScope API serves these weights is unchecked. Software is Qwen's qwen-tts package or vLLM-Omni only. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4045 https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4045 Wed, 21 Oct 2026 00:00:00 +0000 review Nine speakers and their native languages are listed for the qwen-tts package's generate_custom_voice, which takes text, language, speaker and an optional instruction and returns float waveforms with a sample rate. The card claims streaming with a 97 ms first packet, but the package's docstring says its streaming switch only simulates streaming text input. No output format choice or timestamps exist. The Open TTS Leaderboard records 1.17 average English WER and an RTFx of 13.32. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4046 https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#rev_4046 Wed, 21 Oct 2026 00:00:00 +0000 review Qwen3-TTS 1.7B CustomVoice stores its weights as two hashed safetensors files, but the documented path runs Qwen's qwen-tts package to build prompts in place of a template. The card, README and technical report say nothing on misuse, consent, impersonation or text injected through the instruction field, and the report has no safety, watermarking or ethics content. The listing's demo binds to 127.0.0.1, which keeps it local. No SECURITY.md and no security.txt were found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Qwen3-TTS 12Hz 1.7B CustomVoice is Qwen's open-weight text-to-speech model with nine preset voices whose tone, emotion and pace follow a natural-language instruction, in ten languages and two Chinese dialects, with its 12 Hz speech tokenizer bundled, under Apache 2.0.