Search Results for "synthesis" - Page 4
Sort By:
Showing 184 open source projects for "synthesis"
View related business solutions-
Go From Idea to Deployed AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
WhisperSpeech
An Open Source text-to-speech system built by inverting Whisper
...Its architecture follows a token-based, multi-stage pipeline inspired by AudioLM and SPEAR-TTS: Whisper is used to produce semantic tokens, EnCodec compresses the waveform into acoustic tokens, and Vocos reconstructs high-fidelity audio from those tokens. The repository includes notebooks and scripts for inference, long-form synthesis, and finetuning, as well as pre-trained models and converted datasets hosted on Hugging Face. Performance optimizations like torch.compile, KV-caching, and architectural tweaks allow the main model to reach up to 12× real-time speed on a consumer RTX 4090. -
2
VibeVoice ComfyUI
ComfyUI integration for Microsoft's VibeVoice text-to-speech model
...It exposes VibeVoice as a set of custom nodes so you can build single-speaker and multi-speaker voice generation pipelines visually, combining TTS with other audio or generative components. The integration supports high-quality single-speaker synthesis as well as scripted multi-speaker conversations, with optional voice cloning from audio samples for each speaker. It includes advanced control over generation parameters like attention backend, diffusion steps, sampling temperature, guidance scale, and quantization settings, allowing users to tune the trade-offs between quality, VRAM usage, and speed. ... -
3
Tongyi DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
...It uses a mix of synthetic data generation, fine-tuning and reinforcement learning; supports benchmarks like web search, document understanding, question answering, “agentic” tasks; provides inference tools, evaluation scripts, and “web agent” style interfaces. The aim is to enable more autonomous, agentic models that can perform sustained knowledge gathering, reasoning, and synthesis across multiple modalities (web, files, etc.). -
4
Imagen - Pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network
Implementation of Imagen, Google's Text-to-Image Neural Network that beats DALL-E2, in Pytorch. It is the new SOTA for text-to-image synthesis. Architecturally, it is actually much simpler than DALL-E2. It consists of a cascading DDPM conditioned on text embeddings from a large pre-trained T5 model (attention network). It also contains dynamic clipping for improved classifier-free guidance, noise level conditioning, and a memory-efficient unit design. It appears neither CLIP nor prior network is needed after all. ... -
Cut Your Data Warehouse Bill by 54%BigQuery delivers 54% lower TCO with serverless scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
5
Step-Audio 2
Multi-modal large language model designed for audio understanding
Step-Audio2 is an advanced, end-to-end multimodal large language model designed for high-fidelity audio understanding and natural speech conversation: unlike many pipelines that separate speech recognition, processing, and synthesis, Step-Audio2 processes raw audio, reasons about semantic and paralinguistic content (like emotion, speaker characteristics, non-verbal cues), and can generate contextually appropriate responses — including potentially generating or transforming audio output. It integrates a latent-space audio encoder, discrete acoustic tokens, and reinforcement-learning–based training (CoT + RL) to enhance its ability to capture and reproduce voice styles, intonations, and subtle vocal cues. ... -
6
Bert-VITS2
VITS2 backbone with multilingual-bert
...The repository includes everything needed to train, fine-tune, and run the model, from configuration files to preprocessing scripts, spectrogram utilities, and training entrypoints for multi-GPU and multi-node setups. It provides emotional modeling through “emo embeddings,” allowing voices to be conditioned on different affective states during synthesis. Releases include optimizations for Japanese and English alignment, expanded training data, spec caching and pre-generation tools, as well as ONNX export for more lightweight inference deployments. -
7
Stable Diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
...Stability AI's approach to image synthesis has contributed to creating detailed, scalable images while maintaining efficiency. -
8
EmotiVoice
Multi-Voice and Prompt-Controlled TTS Engine
...EmotiVoice provides multiple ways to interact with it, including a web interface, a Docker image, an HTTP API (including an OpenAI-compatible TTS API), and Python scripts for batch synthesis. It also supports voice cloning with your own data, backed by recipes for popular datasets like DataBaker and LJSpeech, so you can train or adapt voices to custom personas. -
9
FluidPatcher
A performance-oriented patch interface for FluidSynth
FluidPatcher is a performance-oriented interface for FluidSynth built using wxpython to create a simple GUI that allows live editing, selecting, and playing of patches. A patch is a collection of settings such as soundfont presets for each MIDI channel, control-change/sysex messages to send when the patch is selected, and midi router or effects settings. Groups of patches are stored in banks, which are saved as human-readable and -editable YAML files. This allows a musician to easily create... -
Powerful App Monitoring Without Surprise BillsTired of monitoring tools that punish you for scaling? AppSignal offers transparent, predictable pricing with every feature unlocked on every plan. Track errors, monitor performance, detect anomalies, and manage logs across Ruby, Python, Node.js, and more. Trusted by developers since 2012 with free dev-to-dev support. No credit card required to start your 30-day trial.
-
10
HEALPix
Data Analysis, Simulations and Visualization on the Sphere
Software for pixelization, hierarchical indexation, synthesis, analysis, and visualization of data on the sphere. Please acknowledge HEALPix by quoting the web page http://healpix.sourceforge.net (or https://healpix.sourceforge.io) and publication: K.M. Gorski et al., 2005, Ap.J., 622, p.759 Full software documentation available at https://healpix.sourceforge.io/documentation.php Wiki Pages: https://sourceforge.net/p/healpix/wiki/Home Exchanging Data with HEALPix (in FITS files): https://sourceforge.net/p/healpix/wiki/Exchanging%20Data%20with%20HEALPix/ GDL and FL users should read https://sourceforge.net/p/healpix/wiki/HEALPix%20and%20GDL/ -
11
RetroScheme- Get Your Retrosynthesis
- RetroScheme is used for molecule sketching and retrosynthesis
... - The App is coupled with molecular sketching tool to sketch your compound - This was made to be easy for the user and can be used endlessly to assist in potential new drug synthesis -
12
Color to Waveform
Convert colors to synth presets
The purpose of the program is to convert a color to a waveform you can use as a synthesizer oscillator inside a DAW such as FL Studio from Image Line. Many synths are provided with an option to load your own waveform, to replace the basic saw, square and sine waveforms commonly used to create synth sounds. The waveform generated by the program will correspond to the subliminal synesthetic sensation of the selected color. You can create your own synth presets to use in a track using color as a base. -
13
ATC-pie
Air traffic control tower and radar simulator (solo + multi-player)
ATC-pie is an air traffic control simulation program. It features solo, multi-player and teacher-student sessions, rendering 3D views of airports through FlightGear. It is essentially designed for realism, and simulates real-life ATC tasks and equipment such as strip racks and sequence management, handovers to/from neighbouring controllers, flight plans, primary & secondary radars, RDF, CPDLC, ATIS recording... -
14
CSM (Conversational Speech Model)
A Conversational Speech Generation Model
The CSM (Conversational Speech Model) is a speech generation model developed by Sesame AI that creates RVQ audio codes from text and audio inputs. It uses a Llama backbone and a smaller audio decoder to produce audio codes for realistic speech synthesis. The model has been fine-tuned for interactive voice demos and is hosted on platforms like Hugging Face for testing. CSM offers a flexible setup and is compatible with CUDA-enabled GPUs for efficient execution. -
15
vits_chinese
Best practice TTS based on BERT and VITS
...The repository offers full training and inference pipelines: preprocessing, mel-spectrogram generation, training scripts, and audio synthesis. For users who don’t train their own models, the project provides pre-trained checkpoints (or instructions) and expects integration with a vocoder during speech synthesis. -
16
VALL-E X
Open source implementation of Microsoft's VALL-E X zero-shot TTS model
...The model attempts to match not just timbre, but also tone, pitch, emotion, and prosody of the reference audio, resulting in highly personalized output. VALL-E-X supports zero-shot cross-lingual synthesis, meaning a monolingual speaker’s voice can be used to speak other languages without additional training. It also preserves aspects of the acoustic environment, such as background noise or reverb, making the generated audio feel more like it came from the same setting as the prompt. The repository includes Python APIs, sample scripts, ready-to-use voice presets, and demos hosted on Hugging Face Spaces and Google Colab so users can try it. -
17
MAIA (MyApp Intelligence Artificial) is designed to provide a foundation for building your own voice-controlled assistant with Python. It uses various libraries and modules for speech recognition, text-to-speech synthesis, and custom functionality.
-
18
Parallel WaveGAN
Unofficial Parallel WaveGAN
...Its main goal is to provide a real-time neural vocoder that can turn mel spectrograms into high-quality speech audio efficiently. The repository is designed to work hand-in-hand with ESPnet-TTS and NVIDIA Tacotron2-style front ends, so you can build complete TTS or singing voice synthesis pipelines. It includes a large collection of “Kaldi-style” recipes for many datasets such as LJSpeech, LibriTTS, VCTK, JSUT, CMU Arctic, and multiple singing voice corpora in Japanese, Mandarin, Korean, and more. The project provides pre-trained models, Colab demos, and example configurations, allowing researchers to quickly evaluate vocoder quality or adapt models to new datasets. -
19
DALL-E 2 - Pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch. The main novelty seems to be an extra layer of indirection with the prior network (whether it is an autoregressive transformer or a diffusion network), which predicts an image embedding based on the text embedding from CLIP. Specifically, this repository will only build out the diffusion prior network, as it is the best performing variant (but which incidentally involves a causal transformer as the denoising network) To train DALLE-2 is a 3 step process, with the training of CLIP being the most important. ... -
20
Text to Waveform
Create synth presets from words
Convert words to waveforms you can load into a synthesizer oscillator to create synth presets. Have fun turning your name, your friends' names, your city name, your pet's name, your team's name into synth presets you can use to produce a track. -
21
Nougat
Implementation of Nougat Neural Optical Understanding
Nougat is a multi-modal generative modeling framework that bridges vision and text modalities with structured generation control (e.g. layout, scene composition) rather than treating images as flat contexts. It combines object-centric modules with transformer-based reasoning to propose, refine, and render scenes in a generative pipeline. The architecture allows you to specify or prompt a layout (which objects should be where) and then the model fills in appearance, context, lighting, and... -
22
DiT (Diffusion Transformers)
Official PyTorch Implementation of "Scalable Diffusion Models"
DiT (Diffusion Transformer) is a powerful architecture that applies transformer-based modeling directly to diffusion generative processes for high-quality image synthesis. Unlike CNN-based diffusion models, DiT represents the diffusion process in the latent space and processes image tokens through transformer blocks with learned positional encodings, offering scalability and superior sample quality. The model architecture parallels large language models but for image tokens—each block refines noisy latent representations toward cleaner outputs through iterative denoising steps. ... -
23
DeepMind Research
Implementations and code to accompany DeepMind publications
...The top level organizes many paper-specific directories across domains such as deep reinforcement learning, self-supervised vision, generative modeling, scientific ML, and program synthesis—for example BYOL, Perceiver/Perceiver IO, Enformer for genomics, MeshGraphNets for physics, RL Unplugged, Nowcasting for weather, and more. Each project folder typically includes its own README, scripts, and notebooks so you can run experiments or explore models in isolation, and many link to associated datasets or external environments like DeepMind Lab and StarCraft II. ... -
24
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
...Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. -
25
NÜWA - Pytorch
Implementation of NÜWA, attention network for text to video synthesis
Implementation of NÜWA, state of the art attention network for text-to-video synthesis, in Pytorch. It also contains an extension into video and audio generation, using a dual decoder approach. It seems as though a diffusion-based method has taken the new throne for SOTA. However, I will continue on with NUWA, extending it to use multi-headed codes + hierarchical causal transformer. I think that direction is untapped for improving on this line of work.
