Audio & Music

Generate music and sound effects from text prompts with AudioCraft

Generate songs from lyrics and style tags with the HeartMuLa music model

Make audio spectrograms and features like mel, chroma and MFCC from the CLI

Transcribe and translate speech in 99 languages with Whisper

Plan and produce a full AI music album with concept, lyrics, track order and export

Generate jingles, beds, voiceovers and sound effects as MP3 or WAV files

Generate narration and voiceover audio from text with built-in OpenAI voices

Queue and fetch generated music for jingles, loops and prototype scoring

Generate text-to-speech narration and voiceovers with streaming and voice options

Generate local speech, transcribe audio and automate dubbing through VoiceStudio's API

Generate songs or instrumental tracks from style prompts and optional lyrics

Turn written content into a two-host conversational podcast episode

Set up Cognitum Music by minting a token and registering its MCP server

Generate a new song from a brief covering genre, mood, language, BPM and theme

Fetch metadata and the audio URL for one music production by its ID

List saved music productions with their metadata and audio links

Master an existing song with LUFS loudness normalization and peak limiting

Extract MIDI and score data from an existing music production

Split an existing song into vocals, drums, bass and other stems

Automate Aivoov tasks with the Rube MCP toolkit from Composio

Automate Castingwords tasks with the Rube MCP toolkit from Composio

Automate Deepgram tasks with the Rube MCP toolkit from Composio

Generate speech with ElevenLabs, browse voices and check usage limits

Automate Gan AI tasks with the Rube MCP toolkit from Composio

Automate Gladia tasks with the Rube MCP toolkit from Composio

Automate Happy Scribe tasks with the Rube MCP toolkit from Composio

Search Listen Notes podcasts and episodes through the Composio Rube MCP server

Generate LMNT text to speech voices and audio through Composio Rube MCP

Record meetings and pull transcripts with Recall.ai through Composio Rube MCP

Transcribe audio and video with Rev AI speech to text through Composio Rube MCP

Manage Spotify playlists, search music and control playback through Composio

Generate music, background tracks and stems with ACE-Step for video

Transcribe audio and video to text with Azure AI Speech for subtitles

Generate neural narration and voiceovers with Azure AI Speech

Generate Mandarin and multilingual narration with Doubao Speech 2.0

Generate voiceovers, sound effects and music with ElevenLabs APIs

Generate expressive multilingual narration with Fish Audio and cloned voices

Add narration, background music and sound effects to HyperFrames compositions

Generate and check music with Google Lyria 3 through the Gemini API

Generate instrumental tracks and songs with lyrics using ElevenLabs Music

Generate sound effects, ambience and impacts from text with ElevenLabs

Transcribe audio and video to text with ElevenLabs Scribe v2 for subtitles

Generate speech audio from text with HeyGen Starfish TTS and voice settings

Edit audio in Audacity from the command line with a stateful CLI

Edit music scores in MuseScore, transpose and export PDF, audio or MIDI

Inspect Rekordbox DJ libraries, build playlists and control live decks from the CLI

Edit music notation, transpose scores and export PDF, audio or MIDI

Turn text or summaries into listenable MP3 audio with local neural text-to-speech

Transcribe uploaded or stored Zoom media in batch jobs with the Scribe API