Whisper AI
Audio & Voice
Whisper AI

Open-source speech recognition for multilingual transcription and translation with AI.

Direct link

Whisper AI by OpenAI is a robust ASR system supporting 99 languages with accent resilience. Ideal for researchers and app developers, it enables accurate transcriptions and translations from audio/video content.

Relevant Sites

Spark-TTS

Spark-TTS is an advanced LLM-powered text-to-speech system delivering highly accurate, natural-sounding voice synthesis for research and production. Efficient, flexible, and powerful.
Kimi-Audio

Kimi-Audio: A universal open-source audio foundation model handling ASR, AQA, AAC & more. Pre-trained on 13M hours for SOTA performance. Features hybrid architecture & low-latency inference.
Descript Voice

Create studio-quality audio with AI voices or your own voice clone – perfect for podcast editing, voiceovers, and content creation.
Notevibes

AI-powered voice agents for 24/7 customer support calls, sales automation, and interactive phone systems.
FakeYou

Entertainment-focused AI voice technology for generating character audio clips, memes, and creative voice content.
Tortoise TTS

Advanced text-to-speech with multi-voice capabilities and natural prosody for professional use.