Open Source Python Text-to-Speech (TTS) Models
Sort By:
Python Text-to-Speech (TTS) Models
View 47 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.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
kokoro-onnx
TTS with kokoro and onnx runtime
kokoro-onnx is a text-to-speech toolkit that wraps the Kokoro neural TTS model in an easy-to-use ONNX Runtime interface, so you can generate speech from Python with minimal setup. It focuses on running efficiently on commodity hardware, including macOS with Apple Silicon, while still delivering near real-time performance for many use cases. The project ships prebuilt model files and a simple example script, so you can go from installation to producing an audio.wav file in just a few steps. It supports multiple languages and voices, with a curated voice list and configuration via a VOICES file hosted alongside the models. The package is distributed on PyPI, meaning you can integrate it directly into applications or scripts using standard Python tooling. It also recommends pairing with an external G2P package to improve pronunciation quality, especially for more complex languages or names, and is licensed under permissive MIT and Apache-style licenses. -
2
MLX-Audio
A text-to-speech, speech-to-text and speech-to-speech library
MLX-Audio is a speech library built on Apple’s MLX framework and optimized for Apple Silicon machines (M-series Macs). It focuses on text-to-speech and speech-to-speech workflows, with APIs and a command-line interface that make it easy to generate high-quality audio from text. Because it uses MLX and targets Apple Silicon, inference is fast and can take advantage of hardware acceleration and quantization for efficient on-device performance. The project provides a straightforward CLI (mlx_audio.tts.generate) as well as a Python API for programmatic generation of audio, including parameters for voice choice, speed, language hints, output format, and sample rate. It includes examples such as audiobook generation to demonstrate long-form synthesis and joined audio segments. On top of that, MLX-Audio offers a modern web interface powered by FastAPI, with real-time waveform and 3D visualizations, file upload, and audio management. -
3
Qwen3-TTS
Qwen3-TTS is an open-source series of TTS models
Qwen3-TTS is an open-source text-to-speech (TTS) project built around the Qwen3 large language model family, focused on generating high-quality, natural-sounding speech from plain text input. It provides researchers and developers with tools to transform text into expressive, intelligible audio, supporting multiple languages and voice characteristics tuned for clarity and fluidity. The project includes pre-trained models and inference scripts that let users synthesize speech locally or integrate TTS into larger pipelines such as voice assistants, accessibility tools, or multimedia generation workflows. Because it’s part of the broader Qwen ecosystem, it benefits from the model’s understanding of linguistic nuances, enabling more accurate pronunciation, prosody, and contextual delivery than many traditional TTS systems. Developers can customize voice output parameters like speed, pitch, and volume, and combine the TTS stack with other AI components. -
4
Kitten TTS
State-of-the-art TTS model under 25MB
KittenTTS is an open-source, ultra-lightweight, and high-quality text-to-speech model featuring just 15 million parameters and a binary size under 25 MB. It is designed for real-time CPU-based deployment across diverse platforms. Ultra-lightweight, model size less than 25MB. CPU-optimized, runs without GPU on any device. High-quality voices, several premium voice options available. Fast inference, optimized for real-time speech synthesis. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
OmniVoice
High-Quality Voice Cloning TTS for 600+ Languages
The OmniVoice project is a cutting-edge multilingual text-to-speech system designed to generate high-quality speech across more than 600 languages. Built on a diffusion language model-style architecture, it combines scalability with strong performance, enabling both natural-sounding voice synthesis and efficient inference speeds. One of its most notable capabilities is zero-shot voice cloning, allowing users to replicate a speaker’s voice using only a short reference audio clip. In addition, it supports voice design through configurable attributes such as gender, accent, pitch, and speaking style, giving users fine-grained control over generated speech. The system also includes advanced features like non-verbal expression tags and pronunciation overrides, enabling expressive and precise output. With support for both API-based and command-line usage, it is designed for research, production, and experimentation alike. -
6
Chatterbox
SoTA open-source TTS
Chatterbox is Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. Try it now on our Hugging Face Gradio app. If you like the model but need to scale or tune it for higher accuracy, check out our competitively priced TTS service (link). It delivers reliable performance with ultra-low latency of sub-200ms—ideal for production use in agents, applications, or interactive media. -
7
GPT-SoVITS
1 min voice data can also be used to train a good TTS model
GPT‑SoVITS is a state-of-the-art voice conversion and TTS system that enables zero‑shot and few‑shot synthesis based on a short vocal sample (e.g., 5 seconds). It supports cross‑lingual speech synthesis across English, Chinese, Japanese, Korean, Cantonese, and more. It's powered by VITS architecture enhanced for few‑sample adaptation and real‑time usability. -
8
OpenVoice
Instant voice cloning by MIT and MyShell. Audio foundation model
OpenVoice is a versatile instant voice cloning system that can replicate a speaker’s tone color from just a short audio clip and then generate speech in multiple languages. It is designed not only to match the timbre of the reference voice, but also to give granular control over style parameters such as emotion, accent, rhythm, pauses, and intonation. The model supports cross-lingual and even zero-shot cross-lingual voice cloning, so a speaker recorded in one language can be made to speak naturally in others. Architecturally, OpenVoice separates “tone color” cloning from style control, which makes it easier to keep a consistent identity while flexibly changing prosody or language. The project provides open-weight models, inference code, and examples, making it suitable both for research and for building production voice experiences. It is actively developed by MyShell, which also integrates OpenVoice into broader agent and entertainment workflows. -
9
Pocket TTS
A TTS that fits in your CPU (and pocket)
Pocket TTS is a lightweight text-to-speech project designed to run efficiently on CPUs, targeting developers who want local speech generation without depending on GPUs or hosted web APIs. It is built to feel practical in everyday applications, where installation and usage should be as simple as adding a dependency and calling a function. The project focuses on keeping the runtime footprint manageable while still producing natural-sounding speech, which makes it attractive for offline tools, prototypes, and privacy-sensitive workflows. Because it is CPU-oriented, it fits well in server environments where GPU access is limited, in desktop apps, or in edge deployments where simplicity matters more than maximum throughput. It also emphasizes developer ergonomics, providing a straightforward API surface that can be integrated into pipelines, assistants, accessibility tools, or batch generation scripts. -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
10
Fish Speech
SOTA Open Source TTS
Fish Speech is a state-of-the-art open-source text-to-speech project that has evolved into the OpenAudio series of advanced TTS models. The repository hosts the code and tooling for training, fine-tuning, and serving high-quality TTS, while the current flagship models (OpenAudio-S1 and S1-mini) are distributed via Fish Audio’s playground and Hugging Face. The models are evaluated with Seed TTS metrics and achieve exceptionally low word and character error rates, indicating strong intelligibility and alignment between text and audio. Fish Speech emphasizes expressive and controllable voices: it supports a long list of emotion tags, tone markers, and special audio effect markers that can be embedded in the text to drive prosody and vocal style, from basic emotions to nuanced states like sarcastic, conciliative, or hysterical. The system is multilingual and cross-lingual, handling multiple languages in a single input without explicit phoneme markup, and is trained on large-scale datasets. -
11
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. -
12
IndexTTS2
Industrial-level controllable zero-shot text-to-speech system
IndexTTS is a modern, zero-shot text-to-speech (TTS) system engineered to deliver high-quality, natural-sounding speech synthesis with few requirements and strong voice-cloning capabilities. It builds on state-of-the-art models such as XTTS and other modern neural TTS backbones, improving them with a conformer-based speech conditional encoder and upgrading the decoder to a high-quality vocoder (BigVGAN2), leading to clearer and more natural audio output. The system supports zero-shot voice cloning — meaning it can mimic a target speaker’s voice from a short reference sample — making it versatile for multi-voice uses. Compared to many open-source TTS tools, IndexTTS emphasizes efficiency and controllability: it offers faster inference, simpler training pipelines, and controllable speech parameters (like duration, pitch, and prosody), which is critical for production use. -
13
Audiblez
Generate audiobooks from e-books
Audiblez is a tool for generating high-quality .m4b audiobooks directly from .epub e-books using the Kokoro-82M neural text-to-speech model. It focuses on making audiobook creation easy and fast: from a single command, the tool splits an e-book into chapters, synthesizes audio for each section, and then merges the results into a structured audiobook with chapter-based WAV files and a final .m4b container. The Kokoro-82M model it uses is compact (82M parameters) yet natural sounding, trained on under 100 hours of audio, and supports multiple languages, including English (US/UK), Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese. Audiblez can run entirely from the command line via a PyPI package or through a simple cross-platform GUI built on wxPython, giving both advanced users and non-technical users an accessible workflow. -
14
VibeVoice
Open-source multi-speaker long-form text-to-speech model
VibeVoice-1.5B is Microsoft’s frontier open-source text-to-speech (TTS) model designed for generating expressive, long-form, multi-speaker conversational audio such as podcasts. Unlike traditional TTS systems, it excels in scalability, speaker consistency, and natural turn-taking for up to 90 minutes of continuous speech with as many as four distinct speakers. A key innovation is its use of continuous acoustic and semantic speech tokenizers operating at an ultra-low frame rate of 7.5 Hz, enabling high audio fidelity with efficient processing of long sequences. The model integrates a Qwen2.5-based large language model with a diffusion head to produce realistic acoustic details and capture conversational context. Training involved curriculum learning with increasing sequence lengths up to 65K tokens, allowing VibeVoice to handle very long dialogues effectively. Safety mechanisms include an audible disclaimer and imperceptible watermarking in all generated audio to mitigate misuse risks. -
15
VoxCPM2
Tokenizer-Free TTS for Multilingual Speech Generation
VoxCPM2 is an advanced open-source text-to-speech system that redefines speech synthesis by eliminating traditional tokenization and instead generating continuous speech representations through a diffusion-based autoregressive architecture. Built on top of the MiniCPM model family, it enables highly natural, expressive, and context-aware speech generation that adapts tone, emotion, and pacing directly from input text. The system is trained on massive multilingual datasets, enabling support for dozens of languages and dialects while maintaining high fidelity and realism in generated audio. VoxCPM stands out for its ability to perform voice cloning with minimal input, capturing not only the speaker’s timbre but also nuanced features such as rhythm, accent, and emotional delivery. It also introduces voice design capabilities, allowing users to generate entirely new voices from natural language descriptions without requiring reference audio. -
16
Resemble Enhance
AI powered speech denoising and enhancement
Resemble Enhance is an AI-powered speech enhancement tool focused on improving the quality of recorded or generated voice audio. It combines denoising and enhancement so speech can sound cleaner, clearer, and more polished. The denoising module separates speech from unwanted background noise, while the enhancement module improves perceptual quality by restoring distortions and extending audio bandwidth. It is useful for voice datasets, podcasts, narration, generated speech, and other workflows where speech clarity matters. The models are trained on high-quality speech data, which helps the tool produce cleaner output than basic filtering alone. Its main value is giving developers and audio creators an open tool for upgrading imperfect speech recordings. -
17
clone-voice
A sound cloning tool with a web interface, using your voice
Clone-voice is a local voice-cloning tool that lets you synthesize speech in any target voice or convert one recording into another voice using the same timbre. It is built around Coqui’s XTTS-v2 model, so it inherits multilingual support and modern neural TTS quality while wrapping it in a user-friendly desktop workflow. The app is designed to be very easy to use: you download a precompiled package, double-click app.exe, and it launches a browser-based web interface where you control cloning and synthesis. It does not require an NVIDIA GPU to run basic tasks, although GPU acceleration can be used when available, making it accessible on modest machines. The tool supports around sixteen languages, including Chinese, English, Japanese, Korean, French, German, Italian, and others, and can capture reference voices directly from a microphone or from uploaded audio. -
18
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. -
19
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. -
20
WhisperLive
A nearly-live implementation of OpenAI's Whisper
WhisperLive is a “nearly live” implementation of OpenAI’s Whisper model focused on real-time transcription. It runs as a server–client system in which the server hosts a Whisper backend and clients stream audio to be transcribed with very low delay. The project supports multiple inference backends, including Faster-Whisper, NVIDIA TensorRT, and OpenVINO, allowing you to target GPUs and different CPU architectures efficiently. It can handle microphone input, pre-recorded audio files, and network streams such as RTSP and HLS, making it flexible for live events, monitoring, or accessibility workflows. Configuration options let you control the number of clients, maximum connection time, and threading behavior so the server can be tuned for different deployment environments. On the client side, you can set the language, whether to translate into English, model size, voice activity detection, and output recording behavior. -
21
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. -
22
MOSS-TTS-Nano
MOSS-TTS-Nano is an open-source multilingual tiny speech generation
MOSS-TTS-Nano is a lightweight text-to-speech model designed for real-time voice generation in resource-constrained environments. It is part of the broader MOSS-TTS family and focuses on delivering high-quality speech synthesis with a compact architecture. The model operates efficiently on CPU-only systems, enabling deployment without specialized hardware. It supports multilingual voice cloning and produces high-fidelity audio with low latency. The system uses an autoregressive audio tokenization pipeline to generate natural-sounding speech. It is suitable for local applications, web services, and embedded systems. Overall, it brings advanced speech synthesis capabilities to lightweight and accessible environments. -
23
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. -
24
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. -
25
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.
