Transcribe spoken audio into text with optional English translation and timestamps.
npx skills add https://github.com/JamesFincher/gengar --skill whisper-jamesfincher
Please help me install this Agent Skill. Skill: whisper Source: https://github.com/JamesFincher/gengar/tree/main/optional-skills/mlops/whisper Command: npx skills add https://github.com/JamesFincher/gengar --skill whisper-jamesfincher
Whisper removes the manual effort of turning spoken audio into accurate written text, including multilingual transcription and optional translation to English.
Use the whisper skill to transcribe the attached audio file and return the full text transcript.
High-intent search queries and answers about installing and using this skill.
Audio transcription and translation to English text are performed by a multilingual speech-to-text model that converts spoken audio into written text. It processes global meetings, interviews, and media content to generate unified transcripts.
Timestamps for subtitles are generated during audio transcription to produce segment timing and word-level timestamps. This structured output supports subtitle creation and makes transcripts searchable for podcast and video content.
Multilingual speech-to-text supports processing meetings and audio content in 99 languages. It identifies or allows specification of the spoken language to accurately transcribe global meetings and international interviews.
Automating meeting-note generation from spoken audio is handled by speech-to-text transcription with configurable timestamp generation. It converts recorded meetings into searchable text for downstream documentation and analysis.
Processing multilingual audio into a single unified transcript involves transcribing spoken segments and optionally translating non-English speech into English text. This creates one cohesive document from diverse language inputs.
A multilingual ASR model runtime is required to transcribe video audio, providing support for transcription and translation tasks. It handles language identification and configurable timestamp generation for subtitle-friendly outputs.
ragnarokhaaTranscribe spoken audio into text using OpenAI's Whisper model.
twjarviszyra-webTranscribe spoken audio into text with timestamps and optional English translation.
Z43LTranscribe spoken audio to text with optional English translation and timestamps.
fikriafConvert spoken language into written text across multiple languages.
