Open Source Python Text-to-Speech (TTS) Models - Page 2
Sort By:
Python Text-to-Speech (TTS) Models
View 14501 business solutionsBrowse free open source Python Text-to-Speech (TTS) Models and projects below. Use the toggles on the left to filter open source Python Text-to-Speech (TTS) Models by OS, license, language, programming language, and project status.
-
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
RealtimeTTS
Converts text to speech in realtime
RealtimeTTS is a low-latency text-to-speech library built for real-time applications such as voice chat with LLMs, assistants, and interactive tools. It is designed around a streaming model: you can feed it text incrementally (for example, as an LLM responds) and get audio output almost immediately, which keeps end-to-end latency very low. The library is engine-agnostic and plugs into a wide range of cloud and local TTS systems, including OpenAI, ElevenLabs, Azure, Coqui, Piper, StyleTTS2, Edge TTS, Google TTS, system TTS and others, so you can swap providers without rewriting your pipeline. It supports both internet-based engines and fully local engines, which lets you choose between privacy, cost, and quality trade-offs. RealtimeTTS also includes robustness features such as automatic fallbacks when a backend fails, so production systems can stay responsive even if one TTS provider is temporarily unavailable. -
2
Speech-AI-Forge
Speech-AI-Forge is a project developed around TTS generation model
Speech-AI-Forge is a full-stack project built around modern text-to-speech generation models, providing both an API server and a Gradio-based web UI for interactive use. At its core, it acts as a hub that wires together multiple speech-related capabilities, including TTS, speech-to-text and LLM-based control flows, behind a consistent interface. The system is designed to be deployed in several ways: you can try it online via hosted demos, spin it up in a one-click Colab environment, run it in Docker containers, or set it up locally with its environment preparation scripts. It is model-agnostic and advertises support for a variety of TTS and speech models such as ChatTTS, CosyVoice, Fish-Speech, FireredTTS and others, as well as Whisper-based ASR, giving you a flexible playground for experimenting with different speech stacks. The project also integrates with general-purpose LLMs (for example GPT- or LLaMA-style models), which can be used to pre-process text, manage conversations. -
3
MetaVoice-1B
Foundational model for human-like, expressive TTS
MetaVoice — in the form of its source repository “metavoice-src” — is a large-scale text-to-speech (TTS) model. Specifically, the base model (MetaVoice-1B) uses around 1.2 billion parameters and has been trained on a massive dataset — reportedly around 100,000 hours of speech data. The goal is to provide human-like, expressive, and flexible TTS: able to generate natural-sounding speech that can handle diverse inputs and likely generalize over voice styles, intonation, prosody, and perhaps multiple languages or accents. With that scale and dataset volume, MetaVoice aims to push the boundary of what open-source TTS models can achieve: high fidelity, natural prosody, and robustness even for edge cases. As a foundational model, it can serve as the backbone for downstream tasks — such as voice generation, voice cloning, speech generation for virtual agents, or even audio production pipelines. -
4
StyleTTS 2
Towards Human-Level Text-to-Speech through Style Diffusion
StyleTTS2 is a state-of-the-art text-to-speech system that aims for human-level naturalness by combining style diffusion, adversarial training, and large speech language models. It extends the original StyleTTS idea by introducing a style diffusion model that can sample rich, realistic speaking styles conditioned on reference speech, allowing highly expressive and diverse prosody. The architecture uses a two-stage training process and leverages an auxiliary speech language model to guide generation toward more natural and coherent utterances. StyleTTS2 supports both single-speaker and multi-speaker configurations, with the ability to sample or transfer styles from reference audio, making it powerful for expressive TTS and character voices. The repository includes training scripts, configuration files, and pre-trained auxiliary modules such as a text aligner, pitch extractor, and PL-BERT-based linguistic encoder. -
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.
-
5
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. 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. -
6
vits_chinese
Best practice TTS based on BERT and VITS
vits_chinese is an implementation of the VITS end-to-end text-to-speech (TTS) architecture tailored for Chinese (and possibly multilingual) speech synthesis. VITS is a model combining variational autoencoders (VAEs), normalizing flows, adversarial learning, and a stochastic duration predictor — a design that enables generation of natural, expressive speech, capturing variations in rhythm and prosody. By customizing or porting VITS for Chinese, this project aims to produce high-quality TTS outputs in a language that can be challenging due to tones, pronunciation variability, and prosody. 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. -
7
GLM-4-Voice
GLM-4-Voice | End-to-End Chinese-English Conversational Model
GLM-4-Voice is an open-source speech-enabled model from ZhipuAI, extending the GLM-4 family into the audio domain. It integrates advanced voice recognition and generation with the multimodal reasoning capabilities of GLM-4, enabling smooth natural interaction via spoken input and output. The model supports real-time speech-to-text transcription, spoken dialogue understanding, and text-to-speech synthesis, making it suitable for conversational AI, virtual assistants, and accessibility applications. GLM-4-Voice builds upon the bilingual strengths of the GLM architecture, supporting both Chinese and English, and is designed to handle long-form conversations with context retention. The repository provides model weights, inference demos, and setup instructions for deploying speech-enabled AI systems. -
8
StoryTeller
Multimodal AI Story Teller, built with Stable Diffusion, GPT, etc.
A multimodal AI story teller, built with Stable Diffusion, GPT, and neural text-to-speech (TTS). Given a prompt as an opening line of a story, GPT writes the rest of the plot; Stable Diffusion draws an image for each sentence; a TTS model narrates each line, resulting in a fully animated video of a short story, replete with audio and visuals. To develop locally, install dev dependencies and install pre-commit hooks. This will automatically trigger linting and code quality checks before each commit. The final video will be saved as /out/out.mp4, alongside other intermediate images, audio files, and subtitles. For more advanced use cases, you can also directly interface with Story Teller in Python code. -
9
VALL-E X
Open source implementation of Microsoft's VALL-E X zero-shot TTS model
VALL-E-X is an open-source implementation of Microsoft’s VALL-E X zero-shot text-to-speech model, focused on multilingual, cross-lingual voice cloning. It is capable of synthesizing speech in English, Chinese, and Japanese from text while mimicking the voice characteristics of a speaker given only a short 3–10 second prompt. 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. -
Compliant and Reliable File Transfers Backed by Top Security CertificationsStop relying on non-certified, legacy file transfer tools that creak under the weight of modern security demands. Get full audit trails, advanced access controls and more supported by an award-winning team of experts. Start your free 25-day trial today.
-
10
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. -
11
Bert-VITS2
VITS2 backbone with multilingual-bert
Bert-VITS2 is a neural text-to-speech project that combines a VITS2 backbone with a multilingual BERT front-end to produce high-quality speech in multiple languages. The core idea is to use BERT-style contextual embeddings for text encoding while relying on a refined VITS2 architecture for acoustic generation and vocoding. 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. -
12
ChatTTS_colab
One-click deployment (including offline integration package)
ChatTTS_colab is a wrapper project around the ChatTTS model that focuses on “one-click” deployment, especially in Google Colab. It provides an integrated offline bundle and scripts for Windows and macOS so users can run ChatTTS locally without wrestling with complex environment setup. The repository includes Colab notebooks that launch a Gradio-based web UI and expose streaming TTS, making it possible to listen to generated audio as it is produced. A distinctive feature is the “voice gacha” system, which batch-generates many distinct voice timbres and allows users to save the ones they like into a curated voice library. It has first-class support for long-form audio generation, making it suitable for audiobooks, podcasts, or long narration tasks. The project also implements multi-speaker or role-based reading, letting users assign different voices to different characters in a script and even use a large language model to generate that script in one step. -
13
DC-TTS
TensorFlow Implementation of DC-TTS: yet another text-to-speech model
DC-TTS is a TensorFlow implementation of the DC-TTS architecture, a fully convolutional text-to-speech system designed to be efficiently trainable while producing natural speech. It follows the “Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention” paper, but the author adapts and extends the design to make it practical for real experiments. The model is split into two networks: Text2Mel, which maps text to mel-spectrograms, and SSRN (spectrogram super-resolution network), which converts low-resolution mel-spectrograms into high-resolution magnitude spectrograms suitable for waveform synthesis. Training scripts, data loaders, and hyperparameter configurations are provided to reproduce results on several datasets, including LJ Speech for English, a Korean single-speaker dataset, and audiobook data from Nick Offerman and Kate Winslet. -
14
Dia
A TTS model capable of generating ultra-realistic dialogue
Dia is a neural text-to-speech model designed specifically for generating ultra-realistic dialogue in a single pass. Instead of focusing on isolated sentences or flat narration, it is optimized for conversational audio, complete with natural turn-taking, prosody, and pacing. The model can be conditioned on a reference audio sample, allowing you to control emotion, tone, and other stylistic aspects of the speech. It can also produce nonverbal vocalizations like laughter, coughs, clearing the throat, and similar sounds, which are crucial for making synthetic conversations feel human. Dia is released with pretrained checkpoints and inference code, with weights hosted on Hugging Face, so researchers and developers can quickly try it or integrate it into pipelines. The base model currently targets English and has around 1.6 billion parameters, offering a strong balance between realism and computational cost, while the ecosystem also includes Dia2. -
15
Dia-1.6B
Dia-1.6B generates lifelike English dialogue and vocal expressions
Dia-1.6B is a 1.6 billion parameter text-to-speech model by Nari Labs that generates high-fidelity dialogue directly from transcripts. Designed for realistic vocal performance, Dia supports expressive features like emotion, tone control, and non-verbal cues such as laughter, coughing, or sighs. The model accepts speaker conditioning through audio prompts, allowing limited voice cloning and speaker consistency across generations. It is optimized for English and built for real-time performance on enterprise GPUs, though CPU and quantized versions are planned. The format supports [S1]/[S2] tags to differentiate speakers and integrates easily into Python workflows. While not tuned to a specific voice, user-provided audio can guide output style. Licensed under Apache 2.0, Dia is intended for research and educational use, with explicit restrictions on misuse like identity mimicry or deceptive content. -
16
FireRedTTS-2
Long-form streaming TTS system for multi-speaker dialogue generation
FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. FireRedTTS2 supports multilingual output and speaker flexibility, enabling scenarios that involve language switching, cross-lingual voice cloning, and expressive dialogue generation that maintains consistency over longer utterances. -
17
GLM-TTS
Controllable & emotion-expressive zero-shot TTS
GLM-TTS is an advanced text-to-speech synthesis system built on large language model technologies that focuses on producing high-quality, expressive, and controllable spoken output, including features like emotion modulation and zero-shot voice cloning. It uses a two-stage architecture where a generative LLM first converts text into intermediate speech token sequences and then a Flow-based neural model converts those tokens into natural audio waveforms, enabling rich prosody and voice character even for unseen speakers. The system introduces a multi-reward reinforcement learning framework that jointly optimizes for voice similarity, emotional expressiveness, pronunciation, and intelligibility, yielding output that can rival commercial options in naturalness and expressiveness. GLM-TTS also supports phoneme-level control and hybrid text + phoneme input, giving developers precise control over pronunciation critical for multilingual or polyphone-rich languages. -
18
MARS5
MARS5 speech model (TTS) from CAMB.AI
MARS5-TTS is CAMB.AI’s open-source English speech model designed for high-quality text-to-speech and voice emulation. It uses a two-stage architecture that combines an autoregressive (AR) model with a non-autoregressive (NAR) model, giving it both expressiveness and speed. The model is built to handle prosodically challenging content such as sports commentary, anime dialogue, and other high-energy or highly varied speech patterns with realistic rhythm and intonation. To control speaker identity, MARS5 uses a short reference audio clip, typically between 2 and 12 seconds, from which it learns the voice characteristics. It supports two main inference modes: shallow clone, which is faster and only needs the reference audio, and deep clone, which additionally uses the transcript of the reference audio to increase similarity and naturalness at the cost of more computation. -
19
Orpheus TTS
Towards Human-Sounding Speech
Orpheus TTS is a state-of-the-art open-source text-to-speech system built on a Llama-3B backbone, treating speech synthesis as a large language model problem instead of a traditional TTS pipeline. It is designed to produce human-like speech with natural intonation, emotion, and rhythm, targeting quality comparable to or better than many closed-source systems. The project ships both pretrained and finetuned English models, as well as a family of multilingual models released as a research preview, and includes data-processing scripts so users can train or finetune their own variants. Inference is provided through a Python package that uses vLLM under the hood for high-throughput, low-latency generation, including streaming examples that show how to generate audio chunks in real time. The maintainers provide Colab notebooks, a standardized prompting format, and one-click deployment via Baseten for production-grade, FP8/FP16 optimized inference with ~200 ms streaming latency. -
20
OuteTTS
Interface for OuteTTS models
OuteTTS is an interface library for running OuteTTS text-to-speech models across a range of backends, making it easier to deploy the same model on different hardware and runtimes. It provides a high-level Interface API that wraps model configuration, speaker handling, and audio generation so you can focus on integrating speech into your application rather than wiring up low-level engines. The project supports multiple backends including llama.cpp (Python bindings and server), Hugging Face Transformers, ExLlamaV2, VLLM and a JavaScript interface via Transformers.js, allowing it to run on CPUs, NVIDIA CUDA GPUs, AMD ROCm, Vulkan-capable GPUs, and Apple Metal. It also includes a notion of speaker profiles: you can create a speaker from a short audio sample, save it as JSON, and reuse it for consistent voice identity across generations and sessions. For best quality, the model is designed to work with a reference speaker clip and will inherit emotion, style, and accent from that reference. -
21
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
Qwen2.5-Omni is an end-to-end multimodal flagship model in the Qwen series by Alibaba Cloud, designed to process multiple modalities (text, images, audio, video) and generate responses both as text and natural speech in streaming real-time. It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds state-of-the-art performance in many multimodal benchmarks, particularly spoken language understanding, audio reasoning, image/video understanding, etc. Very strong benchmark performance across modalities (audio understanding, speech recognition, image/video reasoning) and often outperforming or matching single-modality models at a similar scale. Real-time streaming responses, including natural speech synthesis (text-to-speech) and chunked inputs for low latency interaction. -
22
Sopro TTS
A lightweight text-to-speech model with zero-shot voice cloning
Sopro TTS is an open-source text-to-speech (TTS) project that implements a lightweight model capable of producing speech from text with zero-shot voice cloning, meaning it can mimic a speaker’s voice from only a few seconds of reference audio. Built with a 169 million-parameter architecture that uses dilated convolutions and cross-attention layers instead of large Transformer stacks, it achieves relatively fast real-time performance even on CPUs (about a 0.25 real-time factor measured on an M3 base). The model is designed to work with a small set of dependencies and to be accessible for developers who want offline TTS with customizable voice style, including options for streaming or non-streaming generation modes. Users can install it with standard Python tools, run a demo server locally, and experiment with CLI or Python API usage for producing synthetic speech. -
23
Step-Audio
Open-source framework for intelligent speech interaction
Step-Audio is a unified, open-source framework aimed at building intelligent speech systems that combine both comprehension and generation: it integrates large language models (LLMs) with speech input/output to handle not only semantic understanding but also rich vocal characteristics like tone, style, dialect, emotion, and prosody. The design moves beyond traditional separate-component pipelines (ASR → text model → TTS), instead offering a multimodal model that ingests speech or audio and produces speech accordingly, enabling natural dialogue, voice cloning, and expressive speech synthesis. Through its architecture, Step-Audio supports multilingual interaction, dialects, emotional tones (joy, sadness, etc.), and even more creative speech styles (like rap or singing), while allowing dynamic control over speech characteristics. It also provides a “generative data engine,” which can produce synthetic speech data (cloning voices, varying style) to support TTS training. -
24
Step-Audio-EditX
LLM-based Reinforcement Learning audio edit model
Step-Audio-EditX is an open-source, 3 billion-parameter audio model from StepFun AI designed to make expressive and precise editing of speech and audio as easy as text editing. Rather than treating audio editing as low-level waveform manipulation, this model converts speech into a sequence of discrete “audio tokens” (via a dual-codebook tokenizer) — combining a linguistic token stream and a semantic (prosody/emotion/style) token stream — thereby abstracting audio editing into high-level token operations. This allows users to modify not only what is said (the text) but also how it's said: emotion, tone, speaking style, prosody, accent, even paralinguistic cues. Because the model is trained with a “large-margin learning” objective over many synthesized and natural speech samples, it gains robust control over expressive attributes, and can perform iterative editing: e.g. you could record a line, then ask the model to “make it sadder,” “speak slower,” or “change accent to X.” -
25
Transformer TTS
Implementation of a Transformer based neural network
TransformerTTS is an implementation of a non-autoregressive Transformer-based neural network for text-to-speech, built with TensorFlow 2. It takes inspiration from architectures like FastSpeech, FastSpeech 2, FastPitch, and Transformer TTS, and extends them with its own aligner and forward models. The system separates alignment learning and acoustic modeling: an autoregressive Transformer is used as an aligner to extract phoneme-to-frame durations, while a non-autoregressive “ForwardTransformer” generates mel-spectrograms conditioned on text and durations. This design addresses common autoregressive issues such as repetition, skipped words, and unstable attention, and results in robust, fast synthesis where all frames are predicted in parallel. The repository ships with tooling to build datasets (especially LJSpeech) and create training data, plus scripts to train both the aligner and the TTS model, monitor training with TensorBoard, and resume or reset training runs.