AI Audio

Fun Asr Fun-ASR

Tongyi Lab’s open source end-to-end speech recognition model supports Chinese dialects and 31 languages.

Aero-1-Audio Aero-1-Audio

A lightweight audio model with only 150 million parameters, supporting 15 minutes of continuous audio processing

AInterview AInterview

You are the guest and AI is the host, generating a podcast interview in a few minutes

Fun-AudioGen-VD Alibaba Tongyi Lab

The timbre design model launched by Alibaba Tongyi Lab supports natural language description to generate timbre, emotion and scene-based audio.

AssemblyAI API AssemblyAI

A voice AI API platform for developers, providing a full-link infrastructure from transcription, understanding to voice agent

Gemini 3.1 Flash TTS Google

Next-generation text-to-speech model launched by Google supports 70+ languages ​​and audio tag director-level control

Audio Flamingo Next AF Next

An open source audio language model for long audio understanding that unifies speech, music and ambient sounds into a set of reasoning frameworks

sponge music 海绵音乐

ByteDance’s free AI music creation platform generates singable songs in one sentence

Beatoven Beatoven

AI generates copyright-free background music to customize exclusive soundtracks for videos and podcasts

Castmagic Castmagic

AI-driven podcast content reuse engine that automatically converts audio into show notes, social media posts, timestamps and summaries

Coqui Coqui

Coqui takes executable task flow as its core and emphasizes stable delivery and efficiency improvement.

Descript Overdub

AI voice cloning and dubbing tools, use your voice to say anything