FreeTTS offers online tools for speech generation, transcription, vocal removal, voice enhancement, and audio editing.
NeMo
NVIDIA NeMo provides a framework for language, multimodal, and speech AI, including recognition and text to speech.
About NeMo
NVIDIA NeMo Speech is an open source framework for researchers and PyTorch developers working on Automatic Speech Recognition (ASR), Text-to-Speech (TTS), and Speech LLMs. It provides code and pre-trained model checkpoints to create, customize, and deploy speech models.
The repository now focuses on audio, speech, and multimodal LLMs; the final release before the split with support for additional modalities was v2.7.3. Use requires Python 3.12 or above and PyTorch 2.7 or above, with NVIDIA GPU and CUDA required for training and recommended for inference.
Key features
- Automatic speech recognition including streaming models
- Text-to-speech models including multilingual MagpieTTS
- Speech LLMs and multimodal LLM support
- Pre-trained checkpoints via HuggingFace collection
- Create, customize, and deploy models from existing code
- Installs on existing Python 3.12+ and PyTorch 2.7+ stack
Best for: Researchers and PyTorch developers working on speech recognition, text-to-speech, and speech LLMs.
Good for
- Open source code with pre-trained checkpoints for reuse
- Installs on existing Python/PyTorch/CUDA stack without replacing it
- Covers ASR, TTS, and speech LLMs in one repository
Watch out for
- NVIDIA GPU and CUDA required for training
- Requires Python 3.12 or above and PyTorch 2.7 or above
- Now focused on audio, speech, and multimodal LLMs only
NeMo at a glance
- Category
- AI & Machine Learning › AI Speech Synthesis
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Good for
- Developers, Researchers
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
NeMo alternatives
Tools and sites you could use instead, ranked by how closely they match.
This web app demonstrates text-to-speech using voices from several services.
Open source
24 alternatives
Generate speech from text with Zonos2, an open-weight mixture-of-experts model.
Open source
24 alternatives
Ebook2audiobook converts ebook files or pasted text into audio using a selected language and voice.
This app converts written text to speech with choices for language, model, speaker, and speaking speed.
This app converts entered text into speech and lets users choose a language or model.
Popular in AI Speech Synthesis
Well-known listings from the same topic.
Voice.aivoice.aiSpeechifyspeechify.comSPEECHMAspeechma.comTTS Onlinetext-to-speech.onlineVoice Dreamvoicedream.comElevenReaderelevenreader.io
NeMo FAQ
What is required to run NeMo Speech?
Python 3.12 or above, PyTorch 2.7 or above, and NVIDIA GPU with CUDA for training; GPU with CUDA is recommended for inference.
Where are pre-trained checkpoints available?
Through the project's HuggingFace collection for open weight checkpoints and demos.
Where is support for modalities outside speech?
The repository pivoted to audio, speech, and multimodal LLMs; see v2.7.3 for the final pre-split release with additional modalities.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.