MANIFESTRO DOCS
Console
Get started

Quickstart

Send your first recording and get two speaker tracks back in about five minutes.

Kezek takes a mono recording of two people and returns a separate track for each speaker. The API is asynchronous: you create a job, wait for it to finish, then download the tracks.

1. Create an API key

Open API Keys in the console and create a key. The full key is shown once — store it in an environment variable.

2. Send a recording

Register the file with POST /v1/files, upload the bytes to the pre-signed upload.url, then create the job with its file_id. Or skip the upload and pass a public url. The response is a job in the queued status.

3. Get the result

Poll GET /v1/jobs/{id} until status is completed, or register a webhook for job.completed. The result.tracks array holds a download link per speaker.

Result files are kept for the retention period set in Organization Settings (7 days by default), then deleted.

Next steps

  • Try other settings in the Playground and copy the generated code.
  • Read the Create a job reference for every parameter.
  • Set up Webhooks instead of polling.
Create a job and wait
# 1. Register the file: the answer has its id and a pre-signed upload URL
curl https://api.manifestro.io/v1/files \
  -H "Authorization: Bearer $MANIFESTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"filename": "conversation.wav"}'

# 2. Upload the bytes to upload.url with the headers from upload.headers
curl -X PUT "$UPLOAD_URL" -H "Content-Type: $CONTENT_TYPE" --data-binary @conversation.wav

# 3. Create the job
curl https://api.manifestro.io/v1/jobs \
  -H "Authorization: Bearer $MANIFESTRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "kezek-1", "file_id": "$FILE_ID", "cleanup": "clean", "output_format": "wav", "output": "mono_pair", "sample_rate": 48000}'

# 4. Poll until status is "completed", then download result.tracks[].url
curl https://api.manifestro.io/v1/jobs/$JOB_ID \
  -H "Authorization: Bearer $MANIFESTRO_API_KEY"