Community projects connect Typecast TTS to short-form video, dubbing, narration, audio asset production, agent frameworks, and developer tools. These integrations are built and maintained by third-party developers.
Content and video production
Start here if you are building short-form video, narration, subtitles, character audio, or automated media workflows.
Automate blog publishing and repurpose posts into short-form videos, with Typecast narration and Whisper-derived word timestamps.
Connect Typecast voices, emotions, and loudness controls to AI video generation and CapCut, Premiere, and Vrew export workflows.
Build scenes, captions, multi-voice narration, and CapCut drafts from a script using timestamped TTS.
Generate per-cut MP3 files and SRT subtitles from a narration script with a focused command-line workflow.
Add Typecast narration to automated Instagram, TikTok, and Pinterest affiliate video production.
Use an MCP helper to list voices, generate timestamped speech, and save audio inside a video production monorepo.
Turn uploaded photos into blog posts and short-form videos, using Typecast narration fitted to each video scene.
Batch-generate character reaction audio from a YAML manifest with a small Typecast-focused tool.
Agents and real-time voice
These projects show Typecast inside conversational agents, real-time speech engines, compatibility layers, and evaluation tools.
Add speech generation, voice listing, and voice detail tools to a LlamaIndex agent.
Use streaming Typecast TTS in conversational, real-time voice agents built with TEN Framework.
Use Typecast as a Python real-time TTS engine with voice lookup, emotion controls, and PyAudio streaming.
Explore a local voice assistant that connects speech recognition, an LLM, and Typecast speech synthesis.
Route OpenAI-compatible TTS clients to Typecast through a multi-provider backend. This repository is archived and no longer maintained.
Compare Typecast SSFM 3.0 with other speech models in a crowdsourced blind evaluation platform.
Build a multimodal interactive robot with vision, memory, and Gemini dialogue, using Typecast as an optional asynchronous speech engine.
Generate and play Typecast speech in Discord with a focused JavaScript bot example.
Before you use a project
- Confirm that it uses the current Typecast API or an actively maintained Typecast SDK.
- Keep API keys on the server or in environment variables. Never commit credentials to a repository.
- Check the project's license before copying or distributing its code. Some projects in this list do not declare a license.
- Pin compatible versions and test voice, model, streaming, and timestamp behavior in your own environment.