Integrate ElevenLabs text-to-speech API with Convex backend functions for seamless voice synthesis in web applications.
npm install convex-elevenlabsA Convex component for async speech-to-text transcription using ElevenLabs. Transcriptions are processed asynchronously via webhooks, so your functions return immediately while ElevenLabs processes the audio in the background.
Use convex-elevenlabs to call ElevenLabs API from Convex actions and store generated audio files. The component handles API authentication and provides helper functions for voice synthesis that integrate with Convex's file storage system.
Import convex-elevenlabs functions in your Convex mutations to convert user text to speech audio files. The component processes text input through ElevenLabs voices and returns audio URLs accessible through Convex queries.
convex-elevenlabs provides server-side voice generation by wrapping ElevenLabs API calls within Convex actions. This enables voice synthesis triggered by database changes or user interactions without client-side API exposure.
Yes, convex-elevenlabs requires a valid ElevenLabs API key to function. You'll need to set up your API credentials in Convex environment variables to authenticate requests to ElevenLabs voice synthesis services.
convex-elevenlabs supports different ElevenLabs voice models and voices available through the ElevenLabs API. You can specify voice parameters when calling synthesis functions to use different voice characteristics and models.
convex-elevenlabs integrates with Convex's built-in file storage system to save generated audio files. The component handles the upload process and returns file URLs that can be accessed through standard Convex file queries.
convex-elevenlabs supports the audio formats provided by ElevenLabs API, typically including MP3 and other common audio formats. The specific formats depend on ElevenLabs API capabilities and can be configured through the component's options.