🤖AI RepoIndex
🎙️

Audio & Transcription

Transcribe audio, generate speech

11 tools in this category

Voice-Pro

PythonGPL-3.0

4.2

Gradio WebUI for TTS and voice cloning

11,148 starsNone
Audio & TranscriptionOpen SourceGPU Required

AudioCraft

PythonMIT

4.2

Audio processing and generation by Meta — MusicGen and AudioGen for music and sound

23,476 starsNone
Audio & TranscriptionOpen SourceGPU Required

Buzz

Python/ElectronMIT

4.3

Transcribe and translate audio offline on your personal computer — Whisper without the cloud

20,147 starsNone
Audio & TranscriptionOpen SourceLocal

ChatTTS

PythonAGPL-3.0

4.3

Generative speech model designed specifically for dialogue — best open-source TTS for conversations

39,606 starsNone
Audio & TranscriptionOpen SourceGPU Required

Coqui TTS

PythonMPL-2.0

4.2

Advanced text-to-speech library — multi-language, voice cloning, and speech synthesis

35,000 starsNone
Audio & TranscriptionOpen SourceLocal

Edge TTS

PythonMIT

4.4

Free text-to-speech using Microsoft Edge's neural voices — unlimited, no API key

15,000 starsNone
Audio & TranscriptionOpen SourceAPI Compatible

Fish Speech

PythonMIT

4.2

Open-source TTS with voice cloning

15,000 starsNone
Audio & TranscriptionOpen SourceGPU Required

OpenVoice

PythonMIT

4.3

Instant voice cloning — clone any voice from a short audio reference with MIT and MyShell

36,932 starsNone
Audio & TranscriptionOpen SourceGPU Required

Bark

PythonMIT

4.1

Text-prompted generative audio model — generate speech, music, sound effects from text

39,193 starsNone
Audio & TranscriptionOpen SourceGPU Required

Whisper

PythonMIT

4.8

State-of-the-art speech recognition by OpenAI — run locally or via API

70,000 starsNone
Audio & TranscriptionOpen SourceLocal

Whisper.cpp

C++MIT

4.5

High-performance C++ implementation of Whisper — runs on CPU, no GPU required

70,000 starsNone
Audio & TranscriptionOpen SourceLocal