Speech to Text (Pulse)

Quickstart

View as Markdown

Step 1: Get Your API Key

Open the API Keys page in the Smallest AI console.

Smallest AI dashboard with API Keys highlighted under Developer section in the left sidebar

Click Create API Key in the top-right corner, enter a name, and click Create API Key to confirm.

API Keys page showing the Create API Key button Create New API Key dialog with API Name field and Create API Key button

The new key appears in your dashboard. Click the copy icon to copy it.

API Keys dashboard showing the newly created key with copy icon highlighted

Export the key in your terminal:

$export SMALLEST_API_KEY="your-api-key-here"
New to Smallest AI? Sign up here first.

Step 2: Transcribe Audio

Here’s the sample audio we’ll transcribe:

Paste this cURL (no install required). It downloads the sample and pipes it into Pulse Pro as raw bytes:

$curl -sL "https://github.com/smallest-inc/cookbook/raw/main/speech-to-text/getting-started/samples/audio.wav" | \
>  curl -X POST "https://api.smallest.ai/waves/v1/stt/?model=pulse-pro&language=en" \
>    -H "Authorization: Bearer $SMALLEST_API_KEY" \
>    -H "Content-Type: application/octet-stream" \
>    --data-binary @-

You’ll get back:

1{
2  "status": "success",
3  "transcription": "This is a sample audio file for testing speech-to-text transcription with the Pulse API.",
4  "language": "en",
5  "metadata": { "duration": 5.6, "processing_time_ms": 109.58, "rtfx": 51.1, "num_chunks": 1 },
6  "request_id": "354c932b-3c3a-473c-a6e7-fd497ba10d96"
7}

This quickstart uses Pulse Pro, our leaderboard-ranked English model. If you need multilingual transcription (17 streaming + 26 pre-recorded languages) or streaming, swap ?model=pulse-pro for ?model=pulse. See the Pulse model card for the full language list.

Step 3: Build It Into Your App

The snippets below use Pulse Pro (?model=pulse-pro). For multilingual audio, swap to ?model=pulse and set the appropriate language code. Both models share the same /waves/v1/stt/ endpoint and request shape.

$curl -sL "https://github.com/smallest-inc/cookbook/raw/main/speech-to-text/getting-started/samples/audio.wav" | \
>  curl -X POST "https://api.smallest.ai/waves/v1/stt/?model=pulse-pro&language=en" \
>    -H "Authorization: Bearer $SMALLEST_API_KEY" \
>    -H "Content-Type: application/octet-stream" \
>    --data-binary @-

For Pulse Pro, language must be en. For Pulse, set language to the known code (en, hi, es, etc.) for best accuracy, or use a regional aggregator (multi-eu, multi-indic, multi-asian) for unknown audio. See the Pulse model card for the full language matrix.

Full runnable source files: Python | JavaScript | cURL

Step 4: Explore Features

Real-Time Transcription

Stream audio via WebSocket for live transcription.

Speaker Diarization

Identify and label different speakers.

Word Timestamps

Precise timing for each transcribed word.

Emotion Detection

Analyze emotional tone in speech.

Model card

Benchmarks, capabilities, pricing.

Full endpoint spec: Pulse API Reference

Need Help?

Join Discord

Ask questions and get help from the community.

Or email support@smallest.ai.