{
 "schema_version": 1,
 "generated": "2026-11-09",
 "id": "pyannote-pyannote-audio--find-who-spoke-when-locally-with-pyannote",
 "repo": "pyannote/pyannote-audio",
 "repo_url": "https://github.com/pyannote/pyannote-audio",
 "repo_slug": "pyannote-pyannote-audio",
 "title": "Find who spoke when, locally",
 "page_title": "How to find who spoke when, locally with Pyannote Audio",
 "summary": "Run the community-1 open-source diarization pipeline on your own machine and print each speaker turn with start and stop times.",
 "who": "A developer adding speaker labels to transcripts.",
 "problem": "Transcripts without speaker turns are hard to read and analyze.",
 "outcome": "A list of turns like start=0.2s stop=1.5s speaker_0.",
 "steps": [
  "Install ffmpeg, then `pip install pyannote.audio`",
  "Accept the pyannote/speaker-diarization-community-1 user conditions and create a Hugging Face access token",
  "Load the pipeline with Pipeline.from_pretrained(\"pyannote/speaker-diarization-community-1\", token=...) as in the README",
  "Send it to the GPU when available, run it on audio.wav with a ProgressHook, and loop over output.speaker_diarization to print turns"
 ],
 "agent_prompt": "Using pyannote/pyannote-audio, write a script that loads speaker-diarization-community-1 with my HF token from an environment variable, runs it on <my audio file> with ProgressHook, and saves the turns to a CSV.",
 "agents": [
  "claude-code",
  "codex",
  "cursor",
  "gemini-cli"
 ],
 "difficulty": "Intermediate",
 "time": "30 minutes",
 "basis": "readme",
 "caveat": "Speaker labels are anonymous per file; mapping them to real names is up to you.",
 "category": "Content",
 "tags": [
  "Content"
 ],
 "lang": "",
 "requirements": [
  "ffmpeg installed (needed by torchcodec audio decoding)",
  "Python with `pip install pyannote.audio` or `uv add pyannote.audio`",
  "A Hugging Face access token and accepted user conditions for pyannote/speaker-diarization-community-1; a GPU is optional"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "Keep your Hugging Face token in an environment variable rather than hard coded in scripts."
  },
  {
   "tag": "privacy",
   "notice": "Speaker analysis of recordings of other people needs their consent."
  }
 ],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/pyannote-pyannote-audio/find-who-spoke-when-locally-with-pyannote/",
 "md": "https://dedupedai.com/use-cases/pyannote-pyannote-audio/find-who-spoke-when-locally-with-pyannote/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/pyannote-pyannote-audio--find-who-spoke-when-locally-with-pyannote.json",
 "api_version": "v1"
}
