Audio & Music

Generate narration with TTS, match royalty-free background music and mix with ffmpeg

Avoid media player traps with ExoPlayer audio focus, crossfades and queues

Generate cloned narration with local IndexTTS2 using a reference voice

Generate narrated voice-overs from speaker notes with Azure neural voices

Transcribe audio and video to timestamped, speaker-labeled text locally or remotely

Route audio jobs to StepFun speech tools or to meeting minutes workflows

Transcribe Chinese and English audio with StepFun ASR in one long-form call

Generate Chinese and Japanese speech with StepFun contextual TTS and prosody control

Turn an article into podcast-ready source text for downstream audio synthesis

Submit audio or video for transcription and generate transcripts or subtitles

Pick and tune a Deepgram text-to-speech voice from the curated list or full catalog

Pick and tune an ElevenLabs text-to-speech voice, including custom cloned voices

Generate expressive speech clips with emotion tags using Fish Audio text-to-speech

Transcribe audio and video files into text with your configured speech provider

Transcribe speech in audio files to text with Tencent Cloud ASR

Convert text to MP3 speech with optional read-aloud playback

Generate speech, music, video and images with MiniMax multimodal models

Download a Bilibili video, transcribe it and save the text as Markdown

Download a Douyin video, transcribe it and save the text as Markdown

Download podcast episodes from RSS or links and save transcripts as Markdown

Download a TikTok video, transcribe it and save it as Markdown

Download a Weibo video, transcribe it and save the text as Markdown

Download a YouTube video, transcribe it and save a bilingual Markdown transcript

Download a Zhihu video, transcribe it and save the text as Markdown

Set up HeartMuLa to generate full songs from lyrics and style tags

Generate spectrograms and audio feature plots like mel, chroma and MFCC from files

Generate an instrumental music bed for video ads with ElevenLabs Music

Generate a spoken voiceover for video ads with ElevenLabs text-to-speech

Mix voiceover, music and sidechain ducking for short ads in one FFmpeg pass

Compute loudness, roughness, STI and speech quality metrics for audio in MATLAB

Play, record and stream full-duplex audio in MATLAB with audiostreamer

Build real-time audio chains with EQ, dynamic range control and metering

Write VST and AU audio effect plugins in MATLAB with audioPlugin classes

Ask what GM Farcaster podcast guests said on a topic and get episode summaries

Create music and sung vocals from lyrics with ACE-Step models on Scenario

Generate music, sound effects, voiceover and speech with Scenario audio models

Generate speech, music and sound effects or dub audio with ElevenLabs on Scenario

Generate full songs with vocals from lyrics using MiniMax music models

Add sound effects, foley and music to silent video with Sonilo models

Write song lyrics and craft prompts for Suno AI music generation

Generate speech, music and sound effects through ElevenLabs or OpenAI audio APIs

Extract audio from videos and download audio-only media with yt-dlp

Generate text-to-speech narration and voiceovers with the OpenAI Audio API

Plan and market a podcast with show notes, distribution and discoverability work

Convert text to natural speech with Edge-TTS or OpenAI voices, including Chinese

Transcribe voice messages with Whisper and turn text replies back into speech

Split a stereo music mix into vocals, drums, bass and other stems