workflowstacks
voice-ai

Speech: Build AI Voices

Get scalable speech AI with Speech, a framework for researchers and developers, backed by 18k+ GitHub stars.
18,569 stars+30★ this week3,642 forksPythonGuide quality 8/10 · reviewed Jul 2Updated 10/10/2026100% free · open source
What it does

Speech is a scalable generative AI framework for building Automatic Speech Recognition and Text-to-Speech systems using Large Language Models and Multimodal techniques.

When to use it
  • •When building voice assistants or voice-controlled applications
  • •When developing speech-to-text or text-to-speech systems for content creation or accessibility
  • •When researching or experimenting with multimodal AI models that combine speech, text, and other modalities
Ready-to-paste prompt
python examples/tts.py --model=HiFiGAN --text='Hello, how are you?' --output_file=speech_output.wav
Heads up: Requires a compatible NVIDIA GPU and the CUDA toolkit installed to utilize GPU acceleration, which is a prerequisite for many of the framework's features
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/speech && curl -fsSL https://workflowstacks.com/api/skills/speech/claude-skill -o ~/.claude/skills/speech/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Speech: Build AI Voices works
Codeflow
Free to inspect

Speech: Build AI Voices is a very large Python project (~392k lines across 1044 code files, plus 642 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~392k lines · 1044 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python · Docker
No API keys detected
Python 76%Jupyter Notebook 23%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    examples/__init__.py
    A worked example — copy this to get going
What's in each folder
examples/Examples you can copy298 files
docs/Documentation281 files
tutorials/Examples you can copy87 files
nemo/Folder752 files
scripts/Helper scripts187 files
tools/Helper scripts78 files
external/Community contributions7 files
docker/Deployment / infrastructure1 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
NVIDIA-NeMo
Language
Python
Category
voice-ai
Published
8/5/2019

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/speech.svg)](https://workflowstacks.com/skills/speech?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More voice-ai tools founders pair with this one.

voice-ai★ 212,477
opencode: Code Faster
Get a coding agent with opencode, for founders. Backed by 191k+ GitHub stars.
voice-ai★ 77,690
Unsloth: Train AI Models
Train and run open AI models locally with Unsloth Studio, for founders. 68k+ GitHub stars
voice-ai★ 50,241
airi
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
voice-ai★ 165
VideoHighlighter
Open-source local AI video analyzer powered by Ollama. Visual search, automatic highlights, scene/action/object detection, audio analysis, and subtitle generation. Free, offline alternative to Twelve Labs, Runway, and Descript.
voice-ai★ 224
TypeWhisper: Local Speech-to-Text
Get local speech-to-text with translation for Windows, ideal for startup founders needing on-device dictation and transcription.
voice-ai★ 685
QVAC: Local AI Control
Run AI applications privately with QVAC. For founders building cross-platform AI tools.