Great Work Labs
Models / Write and restructure

Comma

Punctuation and capitalization
comma-1

Fix lowercase, run-on text from speech and chat.

Price$0.02 per 1,000 texts
Speed (our servers)32 to 71 ms
Languages~90 languages (not Thai, Lao, Khmer, Burmese or Tibetan)
InputText, batches up to 64
Built onHorizon-Labs/multilingual-punctuation-truecase-small (Apache-2.0)

Comma puts punctuation and capital letters back into text that lost them: speech-to-text output, chat logs, subtitles, OCR. It adds periods, commas, question marks and colons, capitalizes sentence starts and names, and uppercases acronyms, in about 90 languages.

Pair it with Scribe for clean transcripts, or run it before any model that reads sentences.

Use it

curl https://labs.greatwork.company/v1/run \
  -H "Authorization: Bearer $GWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "comma-1",
  "input": "ok so the plan for q3 is to ship the api first then the dashboard does anyone have concerns about the timeline sarah you mentioned the nasa contract"
}'

Set GWL_API_KEY to a key from your dashboard. The bare name comma works too and follows new versions.

Options

input: A string, or an array of up to 64 strings to run as a batch.

No options: send input and that's it.

Output

FieldTypeMeaning
textstringThe text with punctuation and casing restored.
changesintegerHow many words changed.

Every response wraps this in {"id", "model", "output", "usage": {"units", "unit", "cost_usd"}, "latency_ms"}. Send an array as input and output is an array in the same order.

Examples

Meeting transcript

{
  "model": "comma-1",
  "input": "ok so the plan for q3 is to ship the api first then the dashboard does anyone have concerns about the timeline sarah you mentioned the nasa contract"
}
{
  "text": "Ok, so the plan for Q3 is to ship the API first, then the dashboard. Does anyone have concerns about the timeline? Sarah: You mentioned the NASA contract.",
  "changes": 11
}

Captured on our production servers: 71 ms, 1 text, $0.00002.

German

{
  "model": "comma-1",
  "input": "ich habe gestern mit herrn müller gesprochen er kommt am montag nach berlin"
}
{
  "text": "Ich habe gestern mit Herrn Müller gesprochen. Er kommt am Montag nach Berlin.",
  "changes": 7
}

Captured on our production servers: 32 ms, 1 text, $0.00002.

Good for

  • Clean up raw speech-to-text
  • Fix chat transcripts before summarizing
  • Make subtitles readable
  • Restore casing in all-lowercase data

Limits and caveats

  • Doesn't add exclamation marks, semicolons, quotes or brackets.
  • Mixed-case names come out wrong (Iphone, Mcdonald's).
  • Existing casing is ignored: the output is the model's casing.

Pricing

$0.02 per 1,000 texts. One unit per text up to 2,000 characters; longer texts are split into 2,000-character chunks and each chunk is a unit. Failed calls aren't charged, and a call never costs more than its estimate (POST /v1/estimate tells you before you run it).

Built on

Horizon-Labs/multilingual-punctuation-truecase-small, 140M (mmBERT-small encoder) parameters. License: Apache-2.0. We run it on our servers with our own long-text chunking and score aggregation.