Audio & Music

Transcribe speech from local video files and read Douyin share link metadata

Transcribe voice messages and reply with persona voices using free local speech

Transcribe mp3, m4a, wav and other audio files to text with local whisper

Transcribe local audio, video and Voice Memos quickly with cached MLX Whisper

Transcribe audio in real time or batch with timestamps and speakers in Python

Build real-time speech-to-speech voice assistants over WebSocket in .NET

Hold real-time voice conversations with AI assistants over WebSocket in Java

Build real-time speech-to-speech voice assistants over WebSocket in Python

Build real-time speech-to-speech voice assistants with WebSockets in TypeScript

Transcribe short audio files up to 60 seconds with the Speech to Text REST API

Generate podcast-style audio narratives from content with Azure OpenAI realtime audio

Write songs and Suno prompts with parody, phonetic and lyric-craft techniques

Transcribe audio to text locally on Apple Silicon Macs from wav and other formats

Generate instrumentals, songs and video scores through Mureka, MiniMax and others

Analyze BPM, beats and song structure to plan beat-synced video cuts

Generate voiceovers and sound effects, and keep narration synced to the timeline

Generate game sound effects, ambience and music for Three.js with ElevenLabs

Generate paid Gemini text-to-speech audio for a blog post with an MP3 and embed

Synthesize approved character voiceover lines with CosyVoice TTS for talking videos

Direct expressive text-to-speech for voiceovers, ads and podcast-style narration

Track artist tour dates and find routing gaps with a local Bandsintown cache

Generate speech, voices and audio with ElevenLabs from the command line

Render text to speech, clone voices and transcribe audio with Fish Audio

Pull podcast transcripts as speaker-labeled Markdown and search across episodes

Search the PodcastIndex directory offline, resolve shows and track episode cadence

Search podcast transcripts for mentions, entities and brand safety across shows

Look up concert setlists and predict which songs a band plays next

Control Spotify playback and search music and podcasts from the terminal

Generate songs with Suno and manage a local library of downloaded tracks

Speak short voice summaries of finished work through text to speech

Install and set up voxtype for local voice dictation that types at the cursor

Get the local file path of a voice message the user sent for transcription

Summarize science podcast episodes into key points and takeaways

Transcribe audio files to text with OpenAI Whisper

Extract audio from video files and convert it to WAV for analysis

Turn web pages or text files into audiobooks with automatic TTS fallback

Transcribe audio with Whisper models and align timestamps to speaker segments

Generate natural speech from text with the ElevenLabs text-to-speech API

Compute per-second RMS energy from audio files for volume pattern analysis

Extract, normalize and mix audio tracks with FFmpeg

Convert long text to speech with gTTS, chunking and joining audio segments

Fuse face and lip movement cues with audio to improve speaker diarization in video

Generate natural speech with OpenAI text-to-speech and custom voices

Detect pauses and silences in audio using local adaptive thresholds

Find low-energy silence at the start of audio or video recordings

Choose hierarchical, KMeans or agglomerative clustering to group speaker embeddings

Transcribe video into timestamped text with the Whisper tiny model

Master TTS audio with cleanup, loudness normalization and delivery specs

Detect speech segments with Silero, SpeechBrain or WebRTC voice activity detection