Menu
Synthesis and transcription of speech.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing
Expert knowledge for AI intelligence collection — OSINT methodology, entity extraction, knowledge graphs, change detection, and sentiment analysis
Professional email management — inbox triage, drafting, sending, and follow-up tracking
Expert knowledge for AI lead generation — web research, enrichment, scoring, deduplication, and report generation
Expert knowledge for AI forecasting — superforecasting principles, signal taxonomy, confidence calibration, reasoning chains, and accuracy tracking
| name | voice |
| description | Synthesis and transcription of speech. |
| homepage | https://openai.com/research/whisper |
| metadata | {"version":"1.0.0","category":"multimedia"} |
The Voice capability allows agents to interact with the world through sound. It provides advanced Text-to-Speech (TTS) and Speech-to-Text (STT) powered by OpenAI.
Converts written text into high-quality spoken audio.
text: The message to speak.voice: (Optional) 'alloy', 'echo', 'fable', 'onyx', 'nova', or 'shimmer'.output_path: (Optional) Where to save the resulting .mp3 file.Transcribes audio files into written text.
file_path: Path to an audio file (mp3, wav, etc.).OPENAI_API_KEY is set in the environment.