3b:I[603186,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"PageMetadata"] 3c:I[831915,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"SearchResultsImage"] 3d:I[430295,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],""] 3e:I[299632,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"default"] 3f:I[400402,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"EndpointCTA"] 40:I[331699,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"ModelContent"] 47:I[929847,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"default"] 48:I[946424,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/32q37d2vm9h_s.js","/_next/static/chunks/14sl9ye0a60vb.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/1ttnpl_ih9zxl.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/2drnqf6qy04sf.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42umxct94pn_0.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/08phdxm4si9e6.js","/_next/static/chunks/23fi4qujvabmc.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/1yd7p-515l2jc.js"],"default"] 38:["$","$L3b",null,{"hasPartnerEndpoint":false}] 41:T4fb,Field | Response :---------------------------------------------------------------------------------------------------|:--------------- Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None of the Above Bias Metric (If Measured): | Not Applicable (For GPAI Models): Which characteristic (feature) show(s) the greatest difference in performance?: | Not Applicable (For GPAI Models): Which feature(s) have have the worst performance overall? | Not Applicable Measures taken to mitigate against unwanted bias: | None of the Above (No Human-Trained Data) (For GPAI Models): If using internal data, description of methods implemented in data acquisition or processing, if any, to address the prevalence of identifiable biases in the training, testing, and validation data: | Not Applicable (For GPAI Models): Tools used to assess statistical imbalances and highlight patterns that may introduce bias into AI models: | Not Applicable (For GPAI Models): Not Applicable42:T18b6,# Chatterbox TTS Multilingual Overview ## Description: Chatterbox Multilingual is a 500M-parameter, end-to-end multilingual text-to-speech (TTS) model from Resemble AI. It generates expressive, natural speech across 23 languages using a T3 (Text-to-Speech Token Generator) architecture paired with an S3Gen diffusion-based decoder with flow matching, enabling high-fidelity audio generation and robust cross-lingual synthesis. Chatterbox TTS Multilingual was developed by Resemble AI as a part of Chatterbox. _This model is ready for commercial/non-commercial use._ ## Third-Party Community Consideration This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA [Resemble AI Model Card](https://huggingface.co/ResembleAI/chatterbox). ### License/Terms of Use: Governing Terms: The Chatterbox model governed by the [NVIDIA Open Model Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-agreement/). ADDITIONAL INFORMATION: The Chatterbox base model is governed by [MIT License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md). ### Deployment Geography: Global ### Use Case: Developers building multilingual voice agents, content localization systems, interactive media, language learning tools, and accessibility applications. Suitable for applications requiring expressive, natural speech synthesis in 23 languages. ### Release Date: 26-May, 2026 **Build.Nvidia.com:** https://build.nvidia.com/resemble-ai/chatterbox-multilingual **NGC:** https://registry.ngc.nvidia.com/orgs/nim/containers/chatterbox-multilingual **HuggingFace:** https://huggingface.co/ResembleAI/chatterbox-multilingual **GitHub:** https://github.com/resemble-ai/chatterbox ## Reference(s): [Resemble AI Chatterbox GitHub](https://github.com/resemble-ai/chatterbox) [Chatterbox Multilingual announcement blog](https://www.resemble.ai/chatterbox-multilingual/) [Hugging Face model card](https://huggingface.co/ResembleAI/chatterbox-multilingual) [PerTh Watermarker GitHub](https://github.com/resemble-ai/perth) [NVIDIA API Trial Service Terms of Use / NVIDIA AI Enterprise EULA](https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/) ## Model Architecture: **Architecture Type:** Transformer **Network Architecture:** T3 token generator + S3Gen diffusion decoder with flow matching **Number of model parameters:** 500M (5.0*10^8) ## Input: **Input Type(s):** Text **Input Format(s):** UTF-8 string **Input Parameters:** One-Dimensional (1D) **Other Properties Related to Input:** Input text to synthesize. Language code (BCP-47) required. Emotion exaggeration control: float parameter 0.0-1.0 with recommended range 0.4-0.7. ## Output: **Output Type(s):** Audio **Output Format:** WAV **Output Parameters:** One-Dimensional (1D) **Other Properties Related to Output:** Output is 24 kHz, mono, 16-bit PCM WAV audio. Recommended maximum per generation: ~15 seconds of audio. Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. ## Software Integration: **Runtime Engine(s):** Triton **Supported Hardware Microarchitecture Compatibility:** * NVIDIA Ampere * NVIDIA Hopper * NVIDIA Lovelace **Supported Operating System(s):** Linux The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. This AI model can be embedded as an Application Programming Interface (API) call into the software environment described above. ## Model Version(s): Chatterbox Multilingual v1.0 The model is integrated via NVIDIA NIM (Triton-based microservice) with support for NVIDIA Ampere (A100, A30, A10), Hopper (H100), Lovelace (L4, L40), and Ada (RTX 6000) GPUs. Preferred OS is Linux. The model can be used with the open-source weights or upgraded to the Pro version for enterprise features. ## Training, Testing, and Evaluation Datasets: ## Training Dataset: **Data Modality:** Text **Text Training Data Size:** Less than a Billion Tokens **Data Collection Method by dataset:** Undisclosed **Labeling Method by dataset:** Undisclosed **Properties (Quantity, Dataset Descriptions, Sensor(s)):** Undisclosed ### Testing Dataset: **Data Collection Method by dataset:** Undisclosed **Labeling Method by dataset:** Undisclosed **Properties (Quantity, Dataset Descriptions, Sensor(s)):** Undisclosed ### Evaluation Dataset: **Benchmark Score:** Undisclosed **Data Collection Method by dataset:** Undisclosed **Labeling Method by dataset:** Undisclosed **Properties (Quantity, Dataset Descriptions, Sensor(s)):** Evaluated on diverse multilingual text-to-speech tasks across 23 languages, including stress testing for pronunciation, prosody, and cross-lingual synthesis. ## Key Considerations: Known limitations include variable quality in non-English languages, pronunciation issues in Castilian Spanish, and boundary artifacts in long text handling. ## Inference: **Acceleration Engine:** Triton **Test Hardware:** - NVIDIA A100 GPU - NVIDIA A30 GPU - NVIDIA A10 GPU - NVIDIA H100 GPU - NVIDIA L4 GPU - NVIDIA L40 GPU ## Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).43:Ta29,Field | Response :------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------- Intended Task/Domain: | Speech & Text Model Type: | Transformer Intended Users: | Developers building multilingual voice agents, content localization systems, interactive media, language learning tools, and accessibility applications. Suitable for applications requiring expressive, natural speech synthesis in 23 languages. Output: | Types: Audio. Formats: WAV (For GPAI Models): Tools used to evaluate datasets to identify synthetic data and ensure data authenticity | Not Applicable Describe how the model works: | Chatterbox Multilingual uses a T3 token generator paired with an S3Gen diffusion-based decoder with flow matching to generate expressive, natural speech across 23 languages. Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable Technical Limitations and Mitigation: | This model only has the capacity to produce a voice in the language, dialect and gender(s) in which it is trained. This model makes no effort to moderate or modify input text. Verified to have met prescribed [Insert Company Name Here] quality standards: | Not Applicable Performance Metrics: | Accuracy (Top-1) F-1 Score Throughput & Latency Potential Known Risks: | This model may unnaturally synthesize vocabulary not included in the pronunciation dictionary or omit phonetic symbols not used in training. This model might produce unexpected or inaccurate words or phonemes. Terms of Use/Licensing: | GOVERNING TERMS: [TO BE PROVIDED BY PRODUCT LEGAL VIA NSPECT WORKFLOW]44:T657,Field | Response :----------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------- Generatable or reverse engineerable personal data? | None Personal data used to create this model? | None Known Was consent obtained for any personal data used? | Not Applicable (For GPAI Models): Personal data methods | Not Applicable How often is dataset reviewed? | Before Every Release Is a mechanism in place to honor data subject right of access or deletion of personal data? | Not Applicable Was data from user interactions with the AI model used to train the model? | No Dataset provenance? | Yes Privacy law compliance? | Yes Applicable Privacy Policy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/ (For GPAI Models): Copyright compliance | Not Applicable (For GPAI Models): PII filtering | Not Applicable45:T7d9,### Getting Started Riva uses gRPC APIs. Instructions below demonstrate usage of <%- name %> model using Python gRPC client. ### Prerequisites You will need a system with Git and Python 3+ installed. ### Install Riva Python Client ```bash pip install -U nvidia-riva-client ``` ### Download Python Client Download Python client code by cloning Python Client Repository. ```bash git clone https://github.com/nvidia-riva/python-clients.git ``` ### Run Python Client Open a command terminal and execute below command to synthesize audio from the example text. If you have generated the API key, it will be auto-populated in the command. ```bash python python-clients/scripts/tts/talk.py \ --server grpc.nvcf.nvidia.com:443 --use-ssl \ --metadata function-id "<%- nvcfFunctionId %>" \ --metadata authorization "Bearer <%- apiKey %>" \ --language-code en-US \ --text "this audio is generated from nvidia's text to speech model" \ --voice "Chatterbox-Multilingual.en-US.Male" \ --output audio.wav ``` List of available voices can be obtained using below command. ```bash python python-clients/scripts/tts/talk.py \ --server grpc.nvcf.nvidia.com:443 --use-ssl \ --metadata function-id "<%- nvcfFunctionId %>" \ --metadata authorization "Bearer <%- apiKey %>" \ --list-voices ``` ### Support for gRPC clients in other languages Riva uses gRPC APIs. Proto files can be downloaded from Riva gRPC Proto files and compiled to target language using Protoc compiler. Example Riva clients in C++ and Python languages are provided below. * Python Client Repository * C++ Client Repository 46:Tb4a,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Refer [Supported Models](https://docs.nvidia.com/nim/speech/latest/reference/support-matrix/tts.html) for full list of models. ```bash export NGC_API_KEY= docker run -it --rm --name=chatterbox-tts-multilingual \ --runtime=nvidia \ --gpus '"device=0"' \ --shm-size=8GB \ -e NGC_API_KEY=$NGC_API_KEY \ -e NIM_HTTP_API_PORT=9000 \ -e NIM_GRPC_API_PORT=50051 \ -p 9000:9000 \ -p 50051:50051 \ nvcr.io/nim/nvidia/chatterbox-tts-multilingual:latest ``` It may take up to 30 minutes depending on your network speed, for the container to be ready and start accepting requests from the time the docker container is started. Open a new terminal and run following command to check if the service is ready to handle inference requests ```bash curl -X 'GET' 'http://localhost:9000/v1/health/ready' ``` If the service is ready, you get a response similar to the following. ```bash {"ready":true} ``` ## Step 3. Test the NIM Open a new terminal and run following commands to synthesize audio from text using sample client scripts. Install the Riva Python client package ```bash sudo apt-get install python3-pip pip install -U nvidia-riva-client ``` Download Riva sample clients ```bash git clone https://github.com/nvidia-riva/python-clients.git ``` Run Text to Speech inference in English (en-US) ```bash python3 python-clients/scripts/tts/talk.py --server 0.0.0.0:50051 \ --language-code en-US \ --voice Chatterbox-Multilingual.en-US.Male \ --text "Hello, this is a speech synthesizer." \ --stream \ --output output_english.wav ``` Run Text to Speech inference in Spanish (es-US) ```bash python3 python-clients/scripts/tts/talk.py --server 0.0.0.0:50051 \ --language-code es-US \ --voice Chatterbox-Multilingual.es-US.Male \ --text "Vamos al parque los domingos para jugar con nuestros amigos." \ --stream \ --output output_spanish.wav ``` Run Text to Speech inference in Hindi (hi-IN) ```bash python3 python-clients/scripts/tts/talk.py --server 0.0.0.0:50051 \ --language-code hi-IN \ --voice Chatterbox-Multilingual.hi-IN.Male \ --text "नमस्ते! मुझे आशा है कि आपका दिन बहुत अच्छा रहे" \ --stream \ --output output_hindi.wav ``` On running the above commands, the synthesized audio will be saved to files with corresponding names. You can list available voices with following command. ```bash python3 python-clients/scripts/tts/talk.py --server 0.0.0.0:50051 \ --list-voices ``` For more details on getting started with this NIM, visit the [Riva TTS NIM Docs](https://docs.nvidia.com/nim/speech/latest/tts/index.html).39:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L3c",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/chatterbox-multilingual-tts.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L3d",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/resembleai","children":"Resemble.AI"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"chatterbox-multilingual-tts"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Natural and expressive voices in 23 languages. For voice agents and brand ambassadors."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L3e",null,{"artifactType":"ENDPOINT","density":"standard","labels":["Chatterbox","Speech Generation","TTS","gpuType:endpoint:gpu_type_a100_sxm4_80gb","gpuType:endpoint:gpu_type_dgx_spark","gpuType:endpoint:gpu_type_h100_80gb_hbm3","gpuType:endpoint:gpu_type_l40s","multilingual","nimType:endpoint:nim_type_run_anywhere","usecase:endpoint:usecase_text_to_speech"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L3f",null,{"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L40",null,{"artifact":{"artifactType":"ENDPOINT","name":"chatterbox-multilingual-tts","displayName":"chatterbox-multilingual-tts","publisher":"resembleai","shortDescription":"Natural and expressive voices in 23 languages. For voice agents and brand ambassadors.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/chatterbox-multilingual-tts.jpg","labels":"$39:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"},{"key":"last_month_api_invocation_count","value":"22420"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2026-06-03T19:38:39.980Z","bias":"$41","canGuestDownload":true,"createdDate":"2026-06-03T19:38:39.980Z","description":"$42","explainability":"$43","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$44","safetyAndSecurity":"Field | Response\n:------|:---------\nModel Application(s): | Speech synthesis\nDescribe the life critical impact (if present). | Not Applicable\nModel and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.\nUse case restrictions for the model. | Abide by [https://developer.nvidia.com/riva/ga/license](https://developer.nvidia.com/riva/ga/license)"},"endpointName":"chatterbox-multilingual-tts","endpointSpec":{"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T20:29:38.219Z","nvcfFunctionId":"ddacc747-1269-4fab-bfd9-8f593dead106","createdDate":"2026-06-03T19:38:40.185Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/speech/latest/reference/api-references/tts/protos.html","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License.\n","showUnavailableBanner":false,"cta":"$39:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","usage":"$45","deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$46"}],"specifications":{"parameters":331473663}},"artifactName":"chatterbox-multilingual-tts"},"isLoginRequired":true,"playgroundElement":"$47","publisherName":"resembleai","searchParams":{"model":"chatterbox-multilingual-tts"},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/resembleai/chatterbox-multilingual-tts","aliases":["/resembleai/chatterbox-multilingual-tts/experience"]},{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/resembleai/chatterbox-multilingual-tts/modelcard","aliases":"$undefined"},{"label":"Try API","kind":"default","id":"api","href":"/resembleai/chatterbox-multilingual-tts/api","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/resembleai/chatterbox-multilingual-tts/deploy","aliases":"$undefined"}]}]}]}]]}]] 3a:["$","$L48",null,{"spec":"$39:0:props:children:1:props:children:props:children:props:endpointSpec"}]