skills.rest
metric-space-ai
metric-space-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

transcribe

Transcribe audio to text with optional speaker diarization and known-speaker hints.

2|Updated Apr 12, 2026
Search Tags:#transcript#cli#audio#openai#diarization#transcribe#speakers
One-click install
npx skills add https://github.com/metric-space-ai/ctox --skill transcribe-metric-space-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcribe
Source: https://github.com/metric-space-ai/ctox/tree/main/skills/packs/content/transcribe
Command: npx skills add https://github.com/metric-space-ai/ctox --skill transcribe-metric-space-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Transcribe audio to text with optional speaker diarization and known-speaker hints, enabling quick generation of transcripts from recordings such as interviews, meetings, and podcasts.

Core Features & Use Cases

  • Transcription with optional diarization for speaker labels.
  • Support for multiple output formats: text, json, or diarized_json.
  • Known-speaker hints to anchor transcripts to real individuals and produce readable outputs.

Quick Start

Transcribe this audio file and generate a diarized transcript with speaker labels.

Frequently Asked Questions about transcribe

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio with speaker diarization for meeting recordings?▼

To transcribe audio with speaker diarization, provide the recording file and request speaker labels. The tool processes conversations to generate searchable transcripts with speaker attribution for meetings, interviews, and podcasts.

Can I use known-speaker hints to anchor transcripts to real individuals?▼

Yes, known-speaker hints anchor transcripts to real individuals. You can provide up to four speaker references to produce readable outputs with accurate speaker attribution instead of generic labels.

Do I need an OpenAI API key to transcribe audio into text?▼

Yes, you need an OpenAI API key to transcribe audio into text. The transcription process enforces the OPENAI_API_KEY environment variable to access the underlying OpenAI audio processing services.

What output formats are supported when transcribing audio recordings?▼

Supported output formats for transcribing audio recordings include plain text, JSON, and diarized JSON. The diarized JSON format specifically includes speaker labels for conversations with multiple participants.

Does this transcription tool work with podcasts and interviews?▼

Yes, this transcription tool works with podcasts and interviews. It applies to various recordings needing searchable transcripts with speaker attribution, validating inputs and supporting multiple output formats.

Related Skills

Explore More Data & Analytics Skills→
tiankong0101-bytetiankong0101-byte

openai-whisper

Transcribe audio files into text with timestamps and optional English translation.

Community
Intermediate
DanialHaseebDanialHaseeb

transcribe

Transcribe audio files into text or speaker-labeled JSON segments.

Community
Intermediate
braselogbraselog
3

transcribe

Transcribe meeting audio into text transcripts with optional speaker diarization.

Community
Advanced
koki3141koki3141
2

transcribe

Transcribe audio files into text using OpenAI's API with optional speaker diarization.

Community
Intermediate