inworld-tts
par gugic
Speech & TranscriptionRésumé
Text-to-speech via Inworld.ai API.
Description
Ce que fait ce skill
Generates speech audio from text using the Inworld.ai TTS API. Outputs MP3 files with configurable voice, speaking rate, and temperature. Supports a streaming mode for text exceeding 4000 characters.
Inworld TTS 1.5-max supports streaming for long-form text, which most simple TTS wrappers skip.
Quand l'utiliser
- Converting article text to audio for listening on the go
- Adding spoken responses to a chatbot or assistant
- Generating narration for video or slideshow content
- Producing audio previews of written notifications
- Testing different voice styles for a production app
Exemple de workflow
User asks: convert this blog post to an MP3 with a faster speaking rate
- 1
Reads the blog post text from the source file
- 2
Calls tts.sh with the text, output filename, and --rate 1.4
- 3
Sends the request to the Inworld standard synthesis endpoint
- 4
Writes the decoded audio to the specified MP3 file
An MP3 file containing the narrated blog post at 1.4x speed
Prérequis
- INWORLD_API_KEY environment variable (Base64 key from platform.inworld.ai with 'Voices: Read' permission)
Installation
clawhub install gugic/inworld-ttsExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.