Audio & Transcription
Transcribe audio, generate speech
11 tools in this category
Voice-Pro
Python • GPL-3.0
Gradio WebUI for TTS and voice cloning
AudioCraft
Python • MIT
Audio processing and generation by Meta — MusicGen and AudioGen for music and sound
Buzz
Python/Electron • MIT
Transcribe and translate audio offline on your personal computer — Whisper without the cloud
ChatTTS
Python • AGPL-3.0
Generative speech model designed specifically for dialogue — best open-source TTS for conversations
Coqui TTS
Python • MPL-2.0
Advanced text-to-speech library — multi-language, voice cloning, and speech synthesis
Edge TTS
Python • MIT
Free text-to-speech using Microsoft Edge's neural voices — unlimited, no API key
Fish Speech
Python • MIT
Open-source TTS with voice cloning
OpenVoice
Python • MIT
Instant voice cloning — clone any voice from a short audio reference with MIT and MyShell
Bark
Python • MIT
Text-prompted generative audio model — generate speech, music, sound effects from text
Whisper
Python • MIT
State-of-the-art speech recognition by OpenAI — run locally or via API
Whisper.cpp
C++ • MIT
High-performance C++ implementation of Whisper — runs on CPU, no GPU required