{"id":15219,"date":"2026-11-17T11:03:35","date_gmt":"2026-11-17T02:03:35","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/?p=15219"},"modified":"2026-11-17T11:13:07","modified_gmt":"2026-11-17T02:13:07","slug":"chatterbox-multilingual-v3-gguf-2","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/chatterbox-multilingual-v3-gguf-2\/","title":{"rendered":"chatterbox-GGUF 23-Language Multilingual TTS Model: 4GB+ VRAM"},"content":{"rendered":"<p><!-- lmw:facts --><\/p>\n<h2>At a Glance<\/h2>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Item<\/th>\n<th>Value<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Repository<\/td>\n<td><a href=\"https:\/\/huggingface.co\/ggml-org\/chatterbox-GGUF\">ggml-org\/chatterbox-GGUF<\/a><\/td>\n<\/tr>\n<tr>\n<td>Published<\/td>\n<td>2026-11-06<\/td>\n<\/tr>\n<tr>\n<td>License<\/td>\n<td>mit<\/td>\n<\/tr>\n<tr>\n<td>Formats<\/td>\n<td><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF<\/a><\/td>\n<\/tr>\n<tr>\n<td>Source type<\/td>\n<td>Primary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Values determined by this site&#8217;s code when the information was collected. Dates are JST.<\/em><\/p>\n<p><!-- \/lmw:facts --><\/p>\n<h2>Overview<\/h2>\n<p><code>ggml-org\/chatterbox-GGUF<\/code>, the GGUF quantized version of the open-weight multilingual text-to-speech (TTS) model &#8220;Chatterbox Multilingual V3&#8221; developed by Resemble AI, has been released by ggml-org. This model takes text as input and outputs audio corresponding to 23 languages. It has been converted to the GGUF format using ggml-org&#8217;s automatic conversion tool, enabling efficient speech generation in environments such as <code>llama.cpp<\/code>.<\/p>\n<h2>Specifications<\/h2>\n<p>The specifications and recommended settings described in the documentation for the original model &#8220;ResembleAI\/chatterbox&#8221; and this GGUF distribution model are as follows:<\/p>\n<ul>\n<li><strong>Number of Parameters<\/strong>: 0.5B (500M)<\/li>\n<li><strong>Backbone Architecture<\/strong>: Llama backbone<\/li>\n<li><strong>Processing Capabilities<\/strong>: Text-to-speech (TTS), voice-cloning<\/li>\n<li><strong>Supported Languages<\/strong>: 23 languages (Arabic, Danish, German, Greek, English, Spanish, Finnish, French, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese, Russian, Swedish, Swahili, Turkish, Chinese)<\/li>\n<li><strong>Training Data Volume<\/strong>: 0.5M hours of clean data<\/li>\n<li><strong>Additional Features<\/strong>: PerTh (Perceptual Threshold) embedded watermark output, emotion exaggeration and intensity control<\/li>\n<li><strong>Recommended Steps and Parameters (referencing original model)<\/strong>:<\/li>\n<li>General use (TTS and voice agents): Default settings of <code>exaggeration=0.5<\/code>, <code>cfg=0.5<\/code> are suitable. If the reference speaker speaks quickly, lowering <code>cfg<\/code> to around <code>0.3<\/code> improves the pace. &#8211; Expressive speech: Set a lower <code>cfg<\/code> (e.g., <code>~0.3<\/code>) and increase <code>exaggeration<\/code> to <code>0.7<\/code> or higher. &#8211; Controlling accent inheritance: To mitigate the retention of the reference accent when the reference audio and specified language differ, set the <code>cfg<\/code> weight to <code>0<\/code>.<\/li>\n<li><strong>License Terms<\/strong>: Released under the MIT license, a permissive open-source license.<\/li>\n<\/ul>\n<h2>Performance and Quality<\/h2>\n<p>The model comparison table (Model Zoo) published in the model card of the original model &#8220;ResembleAI\/chatterbox&#8221; is as follows:<\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<p class=\"lmw-table-hint\" style=\"margin:0 0 4px;font-size:0.85em;opacity:0.7;\">\u2192 Scroll horizontally to see all columns<\/p>\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Model<\/th>\n<th>Size<\/th>\n<th>Languages<\/th>\n<th>Key Features<\/th>\n<th>Best For<\/th>\n<th>Demo<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><strong>Chatterbox Multilingual V3<\/strong><\/td>\n<td><strong>500M<\/strong><\/td>\n<td><strong>23+<\/strong><\/td>\n<td>Improved speaker similarity, reduced hallucinations, more natural multilingual speech<\/td>\n<td>Global applications, localization, cross-language voice cloning<\/td>\n<td><a href=\"https:\/\/huggingface.co\/spaces\/ResembleAI\/Chatterbox-Multilingual-TTS-V3\">Demo<\/a><\/td>\n<\/tr>\n<tr>\n<td><strong>Single Language Pack<\/strong><\/td>\n<td>500M each<\/td>\n<td>6 dedicated finetunes<\/td>\n<td>Language- and region-specific quality control<\/td>\n<td>Priority languages and dialect-sensitive applications<\/td>\n<td><a href=\"#single-language-pack\">Demos<\/a><\/td>\n<\/tr>\n<tr>\n<td>Chatterbox<\/td>\n<td>500M<\/td>\n<td>English<\/td>\n<td>CFG and exaggeration tuning<\/td>\n<td>General zero-shot TTS with creative controls<\/td>\n<td><a href=\"https:\/\/huggingface.co\/spaces\/ResembleAI\/Chatterbox\">Demo<\/a><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p>Chatterbox Multilingual V3 supports a wide range of 23+ languages and excels in improving speaker similarity, reducing hallucinations, and generating natural multilingual speech. On the other hand, for use cases requiring strict quality control specialized for specific languages or regional dialects, the dedicated fine-tuned version Single Language Pack is more suitable. Additionally, the English-only Chatterbox excels in creative control features through CFG and exaggeration adjustments.<\/p>\n<p>According to the original model card, Chatterbox Multilingual V3 exhibits higher speaker identity preservation and cross-language accent preservation compared to the conventional V2, making cross-language voice cloning more stable. It is also explained that unnecessary continuous speech and repetitive hallucinations have been reduced. It is claimed to have received high marks in comparative evaluations with commercial systems such as ElevenLabs.<\/p>\n<h2>Strengths and Use Cases<\/h2>\n<p>Based on the specifications of the original model &#8220;ResembleAI\/chatterbox&#8221;, this model excels in use cases that require multilingual speech synthesis and flexible voice cloning. Supported languages span 23 languages including Japanese, English, Chinese, Korean, French, German, Spanish, Russian, and Arabic, enabling reading comprehension across a wide range of languages with a single model.<\/p>\n<p>The model card lists specific use cases such as video content, game audio, meme production, and interactive voice agents. By providing a reference audio file, cross-language voice cloning is possible, allowing the model to speak another language while maintaining the original speaker&#8217;s identity and accent. It is suitable for multilingual localization and global application development while maintaining the voice of the same character.<\/p>\n<p>Furthermore, equipped with control functions to adjust emotional exaggeration and intensity, it is well-suited for creating dramatic and emotionally rich speech in addition to standard calm readings. The generated audio is designed to automatically embed a PerTh neural watermark that remains detectable even after audio editing and MP3 compression.<\/p>\n<p>Note that when more rigorous language-specific behavior or dialect adaptation is required in Chinese, certain regional Spanish, Portuguese, or Hindi for this broad-language model (Chatterbox Multilingual V3), using the dedicated fine-tuned Single Language Pack is recommended.<\/p>\n<p><!-- lmw:hardware --><\/p>\n<h2>Hardware Requirements<\/h2>\n<p><strong>Estimated requirements (calculated by Local Model Watch)<\/strong><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>Your VRAM<\/th>\n<th>Quantization<\/th>\n<th>File size<\/th>\n<th>Est. memory needed<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>4GB (laptop iGPU \/ phone class)<\/td>\n<td>BF16<\/td>\n<td>1.0GB<\/td>\n<td>1.2GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><em>Memory estimates add a 20% runtime overhead (KV cache, etc.) to the actual size of the distributed files. Actual usage varies with context length, batch size and inference engine. These figures are computed by this site from file sizes, not published by the model&#8217;s authors. Compare with other models in our <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-en\/\">VRAM quick reference<\/a>. What the quantization names mean: <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/glossary-quantization-en\/\">glossary<\/a>.<\/em><\/p>\n<p><!-- \/lmw:hardware --><\/p>\n<p><!-- lmw:runnability --><\/p>\n<h2>Can You Run It Locally?<\/h2>\n<p>The publisher distributes this model as GGUF.<\/p>\n<p><strong>License \u2014 <code>mit<\/code> (Commercial use allowed):<\/strong> Permits commercial use, modification and redistribution, provided the copyright notice and license text are retained.<\/p>\n<p><em>Compiled by this site&#8217;s code from the published formats and the license field. License summaries are not legal advice \u2014 check the publisher&#8217;s original terms before relying on them.<\/em><\/p>\n<p><!-- \/lmw:runnability --><\/p>\n<p><!-- lmw:files --><\/p>\n<h2>Distributed Files<\/h2>\n<p><em>Weight files published in <a href=\"https:\/\/huggingface.co\/ggml-org\/chatterbox-GGUF\/tree\/main\">ggml-org\/chatterbox-GGUF<\/a>, listed by this site from the Hugging Face API. Sizes are the actual file sizes.<\/em><\/p>\n<div class=\"lmw-table-scroll\" tabindex=\"0\" style=\"overflow-x:auto;-webkit-overflow-scrolling:touch;max-width:100%;\">\n<table style=\"width:max-content;min-width:100%;border-collapse:collapse;\">\n<thead>\n<tr>\n<th>File<\/th>\n<th>Size<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td><code>chatterbox-BF16.gguf<\/code><\/td>\n<td>1.05GB<\/td>\n<\/tr>\n<tr>\n<td><code>chatterbox-Q8_0.gguf<\/code><\/td>\n<td>559MB<\/td>\n<\/tr>\n<tr>\n<td><code>mmproj-chatterbox-F16.gguf<\/code><\/td>\n<td>595MB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<p><!-- \/lmw:files --><\/p>\n<h2>How to Get It<\/h2>\n<p>This model is distributed in GGUF format via the Hugging Face <code>ggml-org\/chatterbox-GGUF<\/code> repository. No prior consent request or access application is required for use.<\/p>\n<p>To perform inference, a build environment of <code>llama.cpp<\/code> incorporating the necessary updates is required. Once prepared, you can execute speech output from the terminal using the <code>llama-tts<\/code> command.<\/p>\n<pre><code class=\"language-bash\">llama-tts -hf ggml-org\/chatterbox-GGUF -p &quot;Hello world&quot; --tts-lang en --output out.wav\n<\/code><\/pre>\n<p>The language to be spoken is selected with the <code>--tts-lang<\/code> option. If you want to perform voice cloning, specify a reference audio file (wav or mp3 format) using the <code>--tts-speaker-file<\/code> option. If this reference file is not specified, the default voice included with the model is used.<\/p>\n<p>Additionally, you can start a local server using the <code>llama serve<\/code> command and use the text-to-speech function via the <code>\/tts<\/code> endpoint.<\/p>\n<pre><code class=\"language-bash\">llama serve -hf ggml-org\/chatterbox-GGUF\n<\/code><\/pre>\n<p><!-- lmw:related --><\/p>\n<h2>Related Articles<\/h2>\n<ul>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/higgs-audio-v3-stt-gguf\/\">higgs-audio-v3-stt-GGUF Speech-to-Text Model: 4GB+ VRAM, File List<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/soprano-1-1-80m-gguf-released\/\">Soprano-1.1-80M-GGUF Lightweight English TTS Model: File List<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/run-resemble-ai-chatterbox-turbo-locally-gguf\/\">chatterbox-turbo-GGUF Text-to-Speech Model: 4GB+ VRAM, File List<\/a><\/li>\n<li><a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/11\/17\/voxtral-mini-4b-realtime-2602-gguf-2\/\">Voxtral-Mini-4B-Realtime-2602-GGUF Real-time ASR Model: 4GB+ VRAM<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:related --><\/p>\n<p><!-- lmw:next-steps --><\/p>\n<h2>What to Read Next<\/h2>\n<ul>\n<li><strong>Find models by VRAM<\/strong> (This model runs from the 4GB tier) \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/vram-guide-8gb-en\/\">Other models that run on a 8GB GPU<\/a><\/li>\n<li><strong>Formats this model is available in<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/format-gguf-en\/\">GGUF format guide and models<\/a><\/li>\n<li><strong>Other models for the same task<\/strong> \u2192 <a href=\"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/models-by-task-en\/#task-audio\">Other audio models<\/a><\/li>\n<\/ul>\n<p><!-- \/lmw:next-steps --><\/p>\n<h2>Sources<\/h2>\n<ul>\n<li><a href=\"https:\/\/huggingface.co\/ggml-org\/chatterbox-GGUF\">https:\/\/huggingface.co\/ggml-org\/chatterbox-GGUF<\/a><\/li>\n<li><a href=\"https:\/\/huggingface.co\/ResembleAI\/chatterbox\">https:\/\/huggingface.co\/ResembleAI\/chatterbox<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Resemble AI&#8217;s 23-language TTS model Chatterbox Multilingual V3 is now available in GGUF format for llama.cpp.<\/p>\n","protected":false},"author":1,"featured_media":15218,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[203],"tags":[4647,161,163,1073,4649,1547,213],"class_list":["post-15219","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-image-video-and-audio","tag-chatterbox-en","tag-ggml-en","tag-gguf-en","tag-llama-cpp-en","tag-resembleai-en","tag-verified","tag--en"],"lang":"en","translations":{"en":15219,"ja":15217},"_links":{"self":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/15219","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/comments?post=15219"}],"version-history":[{"count":2,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/15219\/revisions"}],"predecessor-version":[{"id":18058,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/posts\/15219\/revisions\/18058"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media\/15218"}],"wp:attachment":[{"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/media?parent=15219"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/categories?post=15219"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/wp-json\/wp\/v2\/tags?post=15219"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}