vibe-knowledge: a Claude Code skill for sourced explainers
vibe-knowledge is a Claude Code skill for sourced explainers: fact checks, narration and 1080p60 rendering, with optional Renoise credits for selected shots.
Published entries across all sections carrying the “Text to speech” tag, newest first by publication date on this site.
21 entries
vibe-knowledge is a Claude Code skill for sourced explainers: fact checks, narration and 1080p60 rendering, with optional Renoise credits for selected shots.
threerocks' MIT-licensed Agent Skill turns an article or topic into a narrated hand-drawn explainer: storyboard timed to the voice, strokes drawn in order.
Eleven v4 reads the script: speaker turns, emotions, pauses and sound effects as text annotations; 90+ language cloning and an AI canvas. SaaS.
Tsinghua NLP lab's open TTS: 2B params, 30 languages, voice design, controllable cloning, 48kHz output, RTF as low as 0.3. Apache-2.0.
Lanshu's agent skill runs the full presenter-video line — script, voice, digital human, lip-sync, render, QA — plus a 12-style route. MIT, 2,924 stars.
Ollama's first speech model, Phonon, landed October 24: local TTS on Apple Silicon, OpenAI-compatible endpoint; English weights Apache 2.0, 40M noncommercial.
Open-source Python framework by Daily: speech, TTS and multimodal pipelines are plug-and-play, multi-agent handoff is built in, SDKs cover seven platforms.
VoxWeft ports VoxCPM2 to MLX for on-device interpretation: first audio in about 170 ms, 30 languages, 5-second voice cloning, nothing leaves the machine.
Ming 3.0 TTS, ASR and audio understanding: 0.5B and 7.9B TTS variants, context-aware transcription, and a 126B audio model with demanding GPU needs.
Tsinghua MAIC open-sourced OpenMAIC: multi-agent lessons with slides, quizzes and interactive simulations, AI teachers and classmates. MIT, 41k stars.
OpenCreator (formerly KrillinAI) reuses Codex CLI as its engine: 12 creator tools for video translation, dubbing, thumbnails and copy. Desktop app ships Codex.
VideoLingo turns video translation into a one-click pipeline: word-level alignment, AI segmentation, glossary translation and dubbing with voice cloning.
Self-hosted meeting middleware. Agents join browser video calls over MCP, read the live transcript and speak or chat, with your choice of LLM and voice.
Adds two-way voice conversations to Claude Code and other agents. Runs offline with local Whisper and Kokoro, or falls back to OpenAI cloud speech services.
VoiceStudio is an open-source ElevenLabs alternative: cloning, dubbing and transcription run locally across 17 TTS and 9 ASR engines, plus MCP for agents.
Under Parker, Stability AI becomes a music AI toolmaker: a $76M round with Sony, Warner and Universal, catalogs licensed, three audio models shipped.
VoxCPM2 by OpenBMB is a 2B-parameter open TTS: 30 languages, 48kHz output, Apache-2.0 licensed, so voiceovers and podcasts can run on your own machine.
ElevenLabs released v4 and v4 Turbo on September 28: 90+ languages, 10-second voice cloning and ~100ms Turbo latency for voice agents, available now via API.
html-explainer is an open-source Agent Skill for Claude Code, Codex and other coding agents: give it a topic and it runs research, narration, voiceover, subtitles, frame-by-frame rendering and covers end to end, producing a hard-subtitled MP4. Scenes are written in HTML/CSS/GSAP and rendered with a deterministic seek renderer, so audio and animation stay locked in sync. The default edge-tts voiceover is free and everything runs locally.
The usual way to narrate a video is pasting a script into a cloud TTS: per-character pricing, generic voices, and your unpublished text on someone else's server. yovoice runs 7 local TTS models through audio.cpp on your own hardware, clones a voice from a 1-60 second clip, and ships a full record-trim-export workflow plus a CLI and an Agent Skill. Apache-2.0, for macOS and Windows.
An open-source tool that converts ebooks into audiobooks entirely on your own machine, with multiple built-in TTS engines, voice cloning, and support for 1,158 languages, producing an m4b with chapters and metadata — no cloud service needed, and it runs on as little as 2GB of RAM.