46:I[603186,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],"PageMetadata"] 47:I[831915,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],"SearchResultsImage"] 48:I[430295,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],""] 49:I[299632,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 4a:I[400402,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],"EndpointCTA"] 4b:I[331699,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],"ModelContent"] 52:I[946424,["/_next/static/chunks/0410xx54a0zpq.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/10aynqa7k04e2.js","/_next/static/chunks/0cnb26qx3wwyi.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/2mn-_kmg2idrw.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/0cz8qgz-kui66.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/0e7pp01hswzc0.js","/_next/static/chunks/2cw7k2bes-1su.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 43:["$","$L46",null,{"hasPartnerEndpoint":false}] 4c:T46c,|Field | Response | |:---------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| |Participation considerations from adversely impacted groups ([protected classes](https://www.senate.ca.gov/content/protected-classes)) in model design and testing: | A2F Model: Age, Gender, Race, Skin Color; A2E (Embedded in A2F) Model: Gender, Accent Variation, Voice Tone Variations | |Measure taken to mitigate against unwanted bias: | A2F Model: Custom dataset that was collected with a range of voices, racial backgrounds, facial structures, and performances to mitigate bias towards one facial structure. A2E (Embedded in A2F) Model: Used dataset in excess of 100 speakers with different vocal timbre, microphones, gender, and accents to make prediction more accurate for wider range of speakers. |4d:T10a2,# Model Overview ## Description NVIDIA Audio2Face-3D is a microservice for animating 3D character's facial characteristics to match any audio track, whether for a game, film, or real-time digital assistant. This model is designed for commercial use. NVIDIA Audio2Emotion is embedded within Audio2Face, and it is designed to automatically recognize the emotions in human speech. These predictions are used to drive the Audio2Face avatar’s facial expressions to make it even more natural. ## Licenses EULA information is available [here](https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/). Customer will use the Software exclusively for authorized purposes, consistent with the Agreement’s terms and all applicable laws, regulations and the rights of others. ## Model Architecture **Architecture Type:**
* Audio2Face: CNN
* Audio2Emotion: Transformer
**Network Architecture**
* Audio2Face: wav2vec2.0
* Audio2Emotion: wav2vec2.0
## Input **Input Type(s):** Audio
**Input Format:** .wav
**Input Parameters: 2D:** (Tuning Parameters and Audio)
**Other Properties Related to Input:** Supported Sampling rates: 22.05KHz, 44.1KHz, 16KHz; All audio is resampled to 16KHz. There is no max audio length.
## Output:
**Output Type(s):**
* Audio2Face: Blendshape Coefficients representing 3D facial animation throughout time
* Audio2Emotion: Emotion Probability Coefficients representing 1D emotion values throughout time
**Output Format:** Custom Protobuf Format
**Output Parameters: 2D:** Custom Protobuf Format
**Other Properties Related to Output:** N/A
## Software Integration **Runtime Engine(s):** * DeepStream-7.1
**Supported Hardware Microarchitecture Compatibility:**
* NVIDIA Ampere
* NVIDIA Hopper
* NVIDIA Lovelace
* NVIDIA Pascal
* NVIDIA Turing
## Preferred/Supported Operating System(s) * Linux
* WSL
## Model Versions:
**Audio2Face:**
* Mark v2.3
* Claire v2.3
* James v2.3
**Audio2Emotion:**
* v1.0
## Training and Evaluation Dataset Data Collection Method by dataset:
* Audio2Face: Human
* Audio2Emotion: Automated
Labeling Method by dataset:
* Human
**Properties (Quantity, Dataset Descriptions, Sensor(s)):** * Audio2Face: Multi-speaker English audio from microphone resampled at 16kHz across multiple audio types and frequency ranges.
* Audio2Emotion: Multi-speaker English audio from microphone resampled at 16kHz across multiple audio types and frequency ranges. The datasets consist of multiple datasets, including RAVDESS, CREMA-D, JL, and Lindy & Rodney. Total quantity: ~18000 samples.
## Inference **Engine:** TensorRT
**Test Hardware:** A100
## 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. When downloaded or used in accordance with our terms of service, 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. You may not use the Software or any of its components for the purpose of emotion recognition. Any technology included in the Software may only be used as fully integrated in the Software and consistent with all applicable documentation. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards [here](https://build.nvidia.com/nvidia/audio2face-3d/modelcard/). Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). ## Disclaimer AI models generate responses and outputs based on complex algorithms and machine learning techniques, and those responses or outputs may be inaccurate or indecent. By testing this model, you assume the risk of any harm caused by any response or output of the model. Please do not upload any confidential information or personal data. Your use is logged for security.4e:Tad3,|Field | Response| |:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| |Intended Applications & Domains: | Video Communication, Teleconferencing, Customer Service, and Game Avatar Creation| |Type: | A2F Model: Facial Animation; A2E (Embedded in A2F) Model: Speech Emotion Recognition, Avatar Animation| |Intended Users: | This model is intended for developers who want to animate the face of virtual avatars in real-time, web camera-based applications.| |Output: | A2F Model: Blendshape Coefficients; A2E (Embedded in A2F) Model: Probability distribution over emotional classes.| |Disclaimer: | Please do not upload any confidential information or personal data. Your use is logged for security. By testing this model, you assume the risk of any harm caused by any response or output of the model. | |Describe how the model works: | Creates a vertex map of facial animation from audio frame-by-frame and converts vertex data to solved blendshape coefficients| |Technical Limitations: | Can be sensitive to varied emotion and audio quality, and emotion recognition may not work well for some voices. AI models generate responses and outputs based on complex algorithms and machine learning techniques, and those responses or outputs may be inaccurate or indecent. | |Verified to have met prescribed NVIDIA quality standards: | Yes| |Performance Metrics: | Accuracy, Visual Inspection| |Potential Known Risks: | Could incorrectly emote or have incorrect lip sync. | |Licensing: | [Community Liscense for Models](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-ai-foundation-models-community-license-agreement/) |4f:T8d3,|Field | Response| |:----------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------| |Generatable or reverse engineerable personally-identifiable information? | None| |Was consent obtained for any personal data used? | A2F Model: Yes; A2E (Embedded in A2F) Model: Not Applicable| |Protected class data used to create this model? | Yes| |How often is dataset reviewed? | Before release | |Is a mechanism in place to honor data subject right of access or deletion of personal data? | A2F Model: Yes; A2E (Embedded in A2F) Model: No| |If personal data collected for the development of the model, was it collected directly by NVIDIA? | A2F Model: Yes; A2E (Embedded in A2F) Model: Not Applicable| |If personal data collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? | A2F Model: Yes; A2E (Embedded in A2F) Model: Not Applicable| |If personal data collected for the development of this AI model, was it minimized to only what was required? | A2F Model: Yes; A2E (Embedded in A2F) Model: Not Applicable| |Is there provenance for all datasets used in training? | Yes| |Does data labeling (annotation, metadata) comply with privacy laws? | Yes, for internal datasets| |Is data compliant with data subject requests for data correction or removal, if such a request was made? | Yes |50:T1192,

Legal

NVIDIA Audio2Face-3D NIM and Authoring Microservice allow you to upload audio files to drive an animation. NVIDIA will only use and store the audio files to provide you with the NVIDIA Audio2Face Authoring Microservice. For more information about our data processing practices, see our Privacy Policy. By clicking “Get API Key” you consent to the processing of your data in accordance with the NVIDIA Cloud Agreement and Service-Specific Terms for NVIDIA Audio2Face 3D Authoring Microservice and NVIDIA Audio2Face 3D Microservice NIM.

### Getting Started Audio2Face uses gRPC APIs. The following instructions demonstrate usage of a model using Python client. The current available models are Mark, Claire, and James. ### Prerequisites You will need a system with Python 3+ installed. ### Prepare Python Client Start by creating a python venv using ```bash $ python3 -m venv .venv $ source .venv/bin/activate ``` ### Download A2F Python Client Download Python client code by cloning [ACE Github Repository](https://github.com/NVIDIA/Audio2Face-3D-Samples/). ```bash $ git clone https://github.com/NVIDIA/Audio2Face-3D-Samples.git $ cd Audio2Face-3D-Samples/scripts/audio2face_3d_api_client ``` Install the proto files by installing the python wheel: ```bash $ pip3 install ../../proto/sample_wheel/nvidia_ace-1.2.0-py3-none-any.whl ``` Then install the required dependencies: ```bash $ pip3 install -r requirements ``` ### Run Python Client To run with Claire model: ```bash $ python ./nim_a2f_3d_client.py ../../example_audio/Claire_neutral.wav config/config_claire.yml \ --apikey <%- apiKey %>\ --function-id 0961a6da-fb9e-4f2e-8491-247e5fd7bf8d ``` To run with Mark model: ```bash $ python ./nim_a2f_3d_client.py ../../example_audio/Claire_neutral.wav config/config_mark.yml \ --apikey <%- apiKey %>\ --function-id 8efc55f5-6f00-424e-afe9-26212cd2c630 ``` To run with James model: ```bash $ python ./nim_a2f_3d_client.py ../../example_audio/Claire_neutral.wav config/config_james.yml \ --apikey <%- apiKey %>\ --function-id 9327c39f-a361-4e02-bd72-e11b4c9b7b5e ``` The script takes four mandatory parameters, an audio file at format PCM 16 bits, a yaml configuration file for the emotions parameters, the API Key generated by API Catalog, and the Function ID used to access the API function. --apikey for the API Key generated through the API Catalog --function-id for the Function ID provided to access the API function for the model of interest ### What does this example do? 1. Reads the audio data from a wav 16bits PCM file 2. Reads emotions and parameters from the yaml configuration file 3. Sends emotions, parameters and audio to the A2F Controller 4. Receives back blendshapes, audio and emotions 5. Saves blendshapes as animation key frames in a csv file with their name, value and time codes 6. Same process for the emotion data. 7. Saves the received audio as out.wav (Should be the same as input audio) ### Connect from any client For gRPC connection from any client, use the following endpoint and function-id alongside the API Key. To generate a new API Key, click the Get API Key button on this page. ``` grpc.nvcf.nvidia.com:443 or https://grpc.nvcf.nvidia.com:443 authorization: Bearer <%- apiKey %> function-id: ``` #### Function IDs Functions with tongue animation enabled (v1.3.16 new feature): Mark model: `8efc55f5-6f00-424e-afe9-26212cd2c630` Claire model: `0961a6da-fb9e-4f2e-8491-247e5fd7bf8d` James model: `9327c39f-a361-4e02-bd72-e11b4c9b7b5e` With tongue animation disabled (for legacy application): Mark model: `cf145b84-423b-4222-bfdd-15bb0142b0fd` Claire model: `617f80a7-85e4-4bf0-9dd6-dcb61e886142` James model: `8082bdcb-9968-4dc5-8705-423ea98b8fc2` 51:T72b,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` Pull and run the NVIDIA NIM with the command below. GPU specific optimized models are available for select GPUs. For using optimized models, refer the [Supported Models](https://docs.nvidia.com/ace/audio2face-3d-microservice/latest/text/getting-started/getting-started.html#supported-models). These profiles are automatically selected when you run Audio2Face-3D NIM. ```bash export NGC_API_KEY= export CONTAINER_NAME=audio2face docker run -it --rm --name=$CONTAINER_NAME \ --gpus all \ --network=host \ -e NGC_API_KEY=$NGC_API_KEY \ nvcr.io/nim/nvidia/audio2face-3d:latest ``` This command will start the NIM container and expose port 52000 for the user to interact with the NIM. If a pre-generated profile is found for your GPU, you will see messages similar to this in the logs: ```bash "timestamp": "XXXX-XX-XX XX:XX:XX", "level": "INFO", "message": "Matched profile_id in manifest from TagsBasedProfileSelector" ``` To list available model profiles: ```bash docker run -it --rm --network=host --gpus all \ --entrypoint nim_list_model_profiles nvcr.io/nim/nvidia/audio2face-3d:latest ``` ```{note} It may take up to 30 minutes depending on your network speed, for the container to be ready and start accepting requests from the time the docker container is started. When starting the service, you might encounter warnings labeled as GStreamer-WARNING. These warnings are safe to ignore as they are not used by Audio2Face-3D. ``` For more details on getting started with this NIM, visit the [NVIDIA Audio2Face-3D Docs](https://docs.nvidia.com/ace/audio2face-3d-microservice/latest/text/getting-started/getting-started.html) 44:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L47",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/audio2face-3d.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","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":[["$","$L48",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"audio2face-3d"}],[["$","span","DEPRECATION",{"className":"nv-badge nv-badge--kind-solid nv-badge--color-red h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Deprecated"]}],["$","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":"Converts streamed audio to facial blendshapes for realtime lipsyncing and facial performances."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L49",null,{"artifactType":"ENDPOINT","density":"standard","labels":["Audio-to-Face","Digital Humans","NVIDIA NIM","nimType:endpoint:nim_type_run_anywhere","usecase:endpoint:usecase_speech_to_animation"],"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",["$","$L4a",null,{"cta":"$undefined","isNIMAccessRestricted":"$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":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L4b",null,{"artifact":{"artifactType":"ENDPOINT","name":"audio2face-3d","displayName":"audio2face-3d","publisher":"nvidia","shortDescription":"Converts streamed audio to facial blendshapes for realtime lipsyncing and facial performances.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/audio2face-3d.jpg","labels":"$44:0: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":"DEPRECATION","value":"04/15/2026"},{"key":"PREVIEW","value":"false"}],"updatedDate":"2025-06-14T16:38:20.480Z","bias":"$4c","canGuestDownload":true,"createdDate":"2024-11-19T18:33:50.399Z","description":"$4d","explainability":"$4e","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$4f","safetyAndSecurity":"|Field | Response |\n|:---------------------------------------------------|:----------------------------------|\n|Model Application(s): | Speech Emotion Recognition, Lip Syncing, Facial Animation|\n|Describe the life-critical impacts (if present). | This model is not designed for life critical applications|\n|Use Case Restriction(s): | See [A2F License](https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/)|\n|Model and Dataset Restriction(s): | 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.|"},"endpointName":"audio2face-3d","endpointSpec":{"namespace":"qc69jvmznzxy","updatedDate":"2026-04-17T01:07:46.494Z","nvcfFunctionId":"a05a5522-3059-4dfd-90e4-4bc1699ae9d4","createdDate":"2024-11-19T18:33:50.750Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/ace/audio2face-3d-microservice/latest/text/interacting/a2f-rpc.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","deprecationNotice":"This API will be deprecated on 04/15/2026. It will no longer be supported after 04/15/2026. Please transition to another model to avoid any service interruptions. For more models information, visit our API Reference.","showUnavailableBanner":false,"iframeUrl":"https://a2f.playground.ngc.nvidia.com?__theme=dark","usage":"$50","deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$51"}]},"artifactName":"audio2face-3d"},"isLoginRequired":true,"playgroundElement":"$undefined","publisherName":"nvidia","searchParams":{},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/audio2face-3d","aliases":["/nvidia/audio2face-3d/experience"]},{"label":"Try API","kind":"default","id":"api","href":"/nvidia/audio2face-3d/api","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/nvidia/audio2face-3d/deploy","aliases":"$undefined"}]}]}]}]]}]] 45:["$","$L52",null,{"spec":"$44:0:props:children:1:props:children:props:children:props:endpointSpec"}]