obul-x402engine-audio

To transcribe audio to text with speaker diarization, this Skill routes your audio file through Deepgram via the Obul proxy. It automatically identifies and separates different speakers in the recording, returning structured written text.

Generating speech from text is handled by sending your script through the Obul proxy to OpenAI or ElevenLabs TTS engines. This Skill abstracts the API integration, allowing you to easily produce high-quality voiceovers.

Yes, you need an OBUL_API_KEY for authentication to use these audio transcription and TTS services. The Skill uses this key to automatically handle all pay-per-use payment processing through the Obul proxy.

You can convert a video script into a voiceover automatically because the Obul proxy manages API payments on a pay-per-use basis. Simply provide the text and select an OpenAI or ElevenLabs voice to generate the audio.

Audio transcription supports identifying different speakers in an interview recording through Deepgram's speaker diarization feature. This processes the spoken words and outputs text structured by each individual speaker.

The primary limitation of using the Obul proxy for speech generation is the strict requirement of an OBUL_API_KEY for authentication and payment routing. You are restricted to the available voices and capabilities of the underlying OpenAI and ElevenLabs APIs.