Skills tagged: tts

• tts - Local TTS and STT on Apple Silicon

  ttssttspeech-synthesisspeech-recognition

  ★ 27 · Updated 2026-09-23

  Provides local text-to-speech, speech-to-text, voice cloning, and subtitle generation using Vox CLI on Apple Silicon.

  ⚙ Synthesize text to speech⚙ Transcribe speech to text⚙ Clone voice from audio sample
• slide-builder - Convert essay-to-speech output into slide decks.

  presentationslidesmarkdownvideo

  ★ 1 · Updated 2026-09-21

  Transforms essay-to-speech output into complete slide decks with Talk Track v5 markdown, supporting HTML and video presentation formats.

  ⚙ Parse essay-to-speech output⚙ Plan slide deck structure⚙ Assess and process slide images
• nemotron-speech - Deploy, run, and test NVIDIA Nemotron Speech NIMs.

  nvidianemotron-speechrivanim

  ★ 0 · Updated 2026-09-21

  Routes NVIDIA Nemotron Speech (Riva) NIM tasks for ASR, TTS, and NMT across cloud-hosted and self-hosted environments.

  ⚙ Deploy ASR TTS and NMT NIMs⚙ Run cloud or self hosted inference⚙ Convert custom NeMo models to NIM
• present - Generate interactive HTML presentations with voiceover narration.

  presentationslideshtmlelevenlabs

  ★ 376 · Updated 2026-09-20

  Converts text content into interactive HTML presentations with dual article and slides mode, synced ElevenLabs voiceover, and custom illustrations.

  ⚙ Generate interactive HTML presentations⚙ Create synchronized voiceover narration⚙ Generate custom slide illustrations
• cyber-persona - CyberPersona Telegram Roleplay System

  cyberpersonaroleplayttstelegram

  ★ 85 · Updated 2026-09-17

  Run CyberPersona roleplay mode with persistent character state, voice, image, and sticker delivery on Telegram.

  ⚙ Start roleplay session⚙ Update persistent character state⚙ Deliver TTS voice messages
• text-to-speech - Convert text to natural speech via inference.sh CLI.

  text-to-speechaudiottsspeech-synthesis

  ★ 748 · Updated 2026-09-17

  Convert text into speech using models such as Inworld, ElevenLabs, DIA, Kokoro, and VibeVoice via the inference.sh CLI.

  ⚙ Convert text to natural speech⚙ Steer speech emotion and delivery⚙ Generate conversational audio
• start - Start a voice conversation with Claude

  voice-chatsttttsmacos

  ★ 2 · Updated 2026-09-16

  Launches whisper.cpp STT and audio capture to initiate a real-time voice chat session on macOS.

  ⚙ Load personality configuration⚙ Start audio server⚙ Register voice chat session
• feishu-voice - Send and receive voice messages on Feishu using ElevenLabs

  feishuvoicettsstt

  ★ 0 · Updated 2026-09-13

  Send voice messages and transcribe received audio files on Feishu using ElevenLabs TTS and STT.

  ⚙ Send voice messages on Feishu⚙ Transcribe audio files with STT⚙ Execute SDK callback test script
• sherpa-onnx-tts - Local text-to-speech via sherpa-onnx

  ttstext-to-speechsherpa-onnxaudio

  ★ 2 · Updated 2026-09-13

  Performs local text-to-speech synthesis using the offline sherpa-onnx CLI without cloud services.

  ⚙ Synthesize speech from text
• kkclaw - Desktop visualization and voice interface for AI Agents.

  desktop-petelectronttsvoice

  ★ 174 · Updated 2026-09-12

  An Electron-based desktop companion supporting sphere visualization, multi-engine speech synthesis, system diagnostics, and OpenClaw Agent synchronization.

  ⚙ Render emotional visual spheres⚙ Synthesize and broadcast voice audio⚙ Synchronize OpenClaw Agent states
• sherpa-onnx-tts - Local offline text-to-speech synthesis via sherpa-onnx

  ttssherpa-onnxspeech-synthesisaudio

  ★ 0 · Updated 2026-09-11

  Performs local text-to-speech synthesis using sherpa-onnx CLI offline without cloud dependencies.

  ⚙ Synthesize speech from text⚙ Generate WAV audio files
• rw-generate-audio - Generate audio using the Runway API

  audio-generationrunwayttssound-effects

  ★ 0 · Updated 2026-09-11

  Generates audio including text-to-speech, sound effects, voice isolation, dubbing, and voice conversion using the Runway API.

  ⚙ Generate text-to-speech audio⚙ Generate sound effects⚙ Isolate voice from audio
• edge-tts-zh - Chinese Text-to-Speech Synthesizer via Edge TTS

  ttstext-to-speechchinese-ttsedge-tts

  ★ 17 · Updated 2026-09-10

  Synthesizes Chinese text into speech audio using the Microsoft Edge TTS engine with customizable voice, rate, pitch, and output formats.

  ⚙ Synthesize Chinese text to speech⚙ Adjust voice speed and pitch⚙ Read input text from file
• pulaoecho-voice-assistant - Remote Audio Voice Assistant

  voice-assistantaudio-streamingttswake-word

  ★ 1 · Updated 2026-09-10

  A remote audio voice assistant supporting voice wake-up and text-to-speech responses.

  ⚙ Detect voice wake-up words⚙ Process speech and natural language⚙ Generate text to speech responses
• personaplex - Generate and validate PersonaPlex voice prompts from Orpheus-TTS audio

  audiottsconversationvalidation

  ★ 7 · Updated 2026-06-30

  Converts Orpheus-TTS persona reference audio into PersonaPlex-native .pt voice prompt files, runs bidirectional offline conversation checks, and writes inspectable publish receipts.

  ⚙ Generate PersonaPlex .pt voice prompts⚙ Create reference packs from receipts⚙ Validate reference pack schema
• epub2podcast-standalone - Convert EPUB to Video Podcast Locally

  epubpodcastsmart-pptsmart-slide

  ★ 219 · Updated 2026-06-30

  Convert EPUB to video podcast with smart slides and dual audio

  ⚙ read EPUB file⚙ generate podcast script⚙ create audio segments
• add-tts - Add Text-to-Speech Audio to Features

  ttsaudiotext-to-speechvoice

  ★ 57 · Updated 2026-03-26

  Adds text-to-speech audio help to features using the TTS system for voice narration and feedback.

  ⚙ create audio hook⚙ design utterances⚙ wire audio into component
• bot-voice-config - Bot Voice Configuration for TTS

  ttsvoiceconfigurationbot

  ★ 33 · Updated 2026-03-24

  Configure and bind Volcengine TTS voices for bots with query and testing support

  ⚙ list available voices⚙ filter voices by style⚙ filter voices by gender
• voice-update - Voice Update - Spoken Status Summary

  voiceaudionotificationtts

  ★ 0 · Updated 2026-02-13

  Provides spoken audio feedback using pocket-tts to announce task completion or summaries

  ⚙ speak text summary via pocket-tts⚙ generate spoken audio
• voice-agent - AI Voice Agent Backend for Local Voice I/O

  voiceaudiospeechtts

  ★ 4 · Updated 2026-02-13

  Provides local voice input and output capabilities for agents through Voice Agent API.

  ⚙ transcribe audio files⚙ synthesize text to audio⚙ check API health

Scroll to load more