curl -H "Authorization: Bearer $SMALLEST_API_KEY" \
  https://waves-api.smallest.ai/api/v1/lightning-v3.1/get_voices

curl --request POST \
  --url "https://waves-api.smallest.ai/api/v1/pulse/get_text?model=pulse&language=en&diarize=true&word_timestamps=true&emotion_detection=true" \
  --header "Authorization: Bearer $SMALLEST_API_KEY" \
  --header "Content-Type: audio/wav" \
  --data-binary "@/path/to/audio.wav"

import os
import requests
<p>API_KEY = os.getenv("SMALLEST_API_KEY")<br>audio_file = "meeting_recording.wav"</p>
<p>url = "<a href="https://waves-api.smallest.ai/api/v1/pulse/get_text" data-framer-link="Link:{"url":"https://waves-api.smallest.ai/api/v1/pulse/get_text","type":"url"}">https://waves-api.smallest.ai/api/v1/pulse/get_text</a>"<br>params = {<br>"model": "pulse",<br>"language": "en",<br>"word_timestamps": "true",<br>"diarize": "true",<br>"emotion_detection": "true"<br>}<br>headers = {<br>"Authorization": f"Bearer {API_KEY}",<br>"Content-Type": "audio/wav"<br>}</p>
<p>with open(audio_file, "rb") as f:<br>audio_data = f.read()</p>
<p>response = requests.post(url, params=params, headers=headers, data=audio_data)<br>result = response.json()</p>
<h1>Print transcription</h1>
<p>print("Transcription:", result.get("transcription"))</p>
<h1>Print word-level details with speaker info</h1>
<p>for word in result.get("words", []):<br>speaker = word.get("speaker", "N/A")<br>print(f"  [Speaker {speaker}] [{word['start']:.2f}s - {word['end']:.2f}s] {word['word']}")</p>
<h1>Check emotions</h1>

const fs = require('fs');<br>const axios = require('axios');<p></p>
<p>const API_KEY = process.env.SMALLEST_API_KEY;<br>const audioFile = 'meeting_recording.wav';</p>
<p>const url = '<a href="https://waves-api.smallest.ai/api/v1/pulse/get_text" data-framer-link="Link:{"url":"https://waves-api.smallest.ai/api/v1/pulse/get_text","type":"url"}">https://waves-api.smallest.ai/api/v1/pulse/get_text</a>';<br>const params = new URLSearchParams({<br>model: 'pulse',<br>language: 'en',<br>word_timestamps: 'true',<br>diarize: 'true',<br>emotion_detection: 'true'<br>});</p>
<p>const audioData = fs.readFileSync(audioFile);</p>
<p>axios.post(<code>${url}?${params}</code>, audioData, {<br>headers: {<br>'Authorization': <code>Bearer ${API_KEY}</code>,<br>'Content-Type': 'audio/wav'<br>}<br>})<br>.then(res => {<br>console.log('Transcription:', res.data.transcription);</p>

{<br>"status": "success",<br>"transcription": "Hello, this is a test transcription.",<br>"words": [<br>{"start": 0.0, "end": 0.88, "word": "Hello,", "confidence": 0.82, "speaker": 0, "speaker_confidence": 0.61},<br>{"start": 0.88, "end": 1.04, "word": "this", "confidence": 1.0, "speaker": 0, "speaker_confidence": 0.76},<br>{"start": 1.04, "end": 1.20, "word": "is", "confidence": 1.0, "speaker": 0, "speaker_confidence": 0.99},<br>{"start": 1.20, "end": 1.36, "word": "a", "confidence": 1.0, "speaker": 0, "speaker_confidence": 0.99},<br>{"start": 1.36, "end": 1.68, "word": "test", "confidence": 0.99, "speaker": 0, "speaker_confidence": 0.99},<br>{"start": 1.68, "end": 2.16, "word": "transcription.", "confidence": 0.99, "speaker": 0, "speaker_confidence": 0.99}<br>],<br>"utterances": [<br>{"start": 0.0, "end": 2.16, "text": "Hello, this is a test transcription.", "speaker": 0}<br>],<br>"age": "adult",<br>"gender": "female",<br>"emotions": {<br>"happiness": 0.28,<br>"sadness": 0.0,<br>"anger": 0.0,<br>"fear": 0.0,<br>"disgust": 0.0<br>},<br>"metadata": {<br>"duration": 1.97,<br>"fileSize": 63236<br>}<br>

import asyncio<br>import json<br>import os<br>import numpy as np<br>import websockets<br>import librosa<br>from urllib.parse import urlencode<p></p>
<p>WS_URL = "wss://waves-api.smallest.ai/api/v1/pulse/get_text"</p>
<h1>Configurable features</h1>
<p>LANGUAGE = "en"<br>ENCODING = "linear16"<br>SAMPLE_RATE = 16000<br>WORD_TIMESTAMPS = False<br>FULL_TRANSCRIPT = True<br>SENTENCE_TIMESTAMPS = False<br>DIARIZE = False<br>REDACT_PII = False<br>REDACT_PCI = False</p>
<p>async def transcribe(audio_file: str, api_key: str):<br>params = {<br>"language": LANGUAGE,<br>"encoding": ENCODING,<br>"sample_rate": SAMPLE_RATE,<br>"word_timestamps": str(WORD_TIMESTAMPS).lower(),<br>"full_transcript": str(FULL_TRANSCRIPT).lower(),<br>"sentence_timestamps": str(SENTENCE_TIMESTAMPS).lower(),<br>"diarize": str(DIARIZE).lower(),<br>"redact_pii": str(REDACT_PII).lower(),<br>"redact_pci": str(REDACT_PCI).lower(),<br>}</p>
<pre><code>url = f"{WS_URL}?{urlencode(params)}"
headers = {"Authorization": f"Bearer {api_key}"}

# Load audio with librosa (handles any format)
audio, _ = librosa.load(audio_file, sr=SAMPLE_RATE, mono=True)
chunk_duration = 0.1  # 100ms chunks
chunk_size = int(chunk_duration * SAMPLE_RATE)

async with websockets.connect(url, additional_headers=headers) as ws:
    print("✅ Connected to Pulse STT WebSocket")
    
    async def send_audio():
        for i in range(0, len(audio), chunk_size):
            chunk = audio[i:i + chunk_size]
            pcm16 = (chunk * 32768.0).astype(np.int16).tobytes()
            await ws.send(pcm16)
            await asyncio.sleep(chunk_duration)
        await ws.send(json.dumps({"type": "end"}))
        print("📤 Sent end signal")

    async def receive_responses():
        async for message in ws:
            result = json.loads(message)
            
            if result.get("is_final"):
                print(f"✓ {result.get('transcript')}")
                
                if result.get("is_last"):
                    if result.get("full_transcript"):
                        print(f"\n{'='*60}")
                        print("FULL TRANSCRIPT")
                        print(f"{'='*60}")
                        print(result.get("full_transcript"))
                    break

    await asyncio.gather(send_audio(), receive_responses())
</code></pre>
<h1>Usage</h1>

export SMALLEST_API_KEY="your-api-key"<br>python transcribe.py recording.wav

const fs = require("fs");<br>const WebSocket = require("ws");<br>const wav = require("wav");<p></p>
<p>const WS_URL = "wss://waves-api.smallest.ai/api/v1/pulse/get_text";</p>
<p>// Configurable features<br>const LANGUAGE = "en";<br>const ENCODING = "linear16";<br>const SAMPLE_RATE = 16000;<br>const WORD_TIMESTAMPS = false;<br>const FULL_TRANSCRIPT = true;<br>const DIARIZE = false;<br>const REDACT_PII = false;<br>const REDACT_PCI = false;</p>
<p>async function loadAudio(audioFile) {<br>return new Promise((resolve, reject) => {<br>const reader = new wav.Reader();<br>const chunks = [];</p>
<pre><code>reader.on("format", (format) =&gt; {
  reader.on("data", (chunk) =&gt; chunks.push(chunk));
  reader.on("end", () =&gt; {
    const buffer = Buffer.concat(chunks);
    const samples = new Int16Array(buffer.buffer, buffer.byteOffset, buffer.length / 2);
    resolve(samples);
  });
});

reader.on("error", reject);
fs.createReadStream(audioFile).pipe(reader);
</code></pre>
<p>});<br>}</p>
<p>async function transcribe(audioFile, apiKey) {<br>const params = new URLSearchParams({<br>language: LANGUAGE,<br>encoding: ENCODING,<br>sample_rate: SAMPLE_RATE,<br>word_timestamps: WORD_TIMESTAMPS,<br>full_transcript: FULL_TRANSCRIPT,<br>diarize: DIARIZE,<br>redact_pii: REDACT_PII,<br>redact_pci: REDACT_PCI,<br>});</p>
<p>const url = <code>${WS_URL}?${params}</code>;<br>const audio = await loadAudio(audioFile);<br>const chunkDuration = 0.1; // 100ms<br>const chunkSize = Math.floor(chunkDuration * SAMPLE_RATE);</p>
<p>return new Promise((resolve, reject) => {<br>const ws = new WebSocket(url, {<br>headers: { Authorization: <code>Bearer ${apiKey}</code> },<br>});</p>
<pre><code>ws.on("open", async () =&gt; {
  console.log("✅ Connected to Pulse STT WebSocket");
  
  for (let i = 0; i &lt; audio.length; i += chunkSize) {
    const chunk = audio.slice(i, i + chunkSize);
    ws.send(Buffer.from(chunk.buffer, chunk.byteOffset, chunk.byteLength));
    await new Promise((r) =&gt; setTimeout(r, chunkDuration * 1000));
  }
  ws.send(JSON.stringify({ type: "end" }));
  console.log("📤 Sent end signal");
});

ws.on("message", (data) =&gt; {
  const result = JSON.parse(data.toString());
  
  if (result.is_final) {
    console.log(`✓ ${result.transcript}`);
    
    if (result.is_last) {
      if (result.full_transcript) {
        console.log("\n" + "=".repeat(60));
        console.log("FULL TRANSCRIPT");
        console.log("=".repeat(60));
        console.log(result.full_transcript);
      }
      ws.close();
    }
  }
});

ws.on("close", resolve);
ws.on("error", reject);
</code></pre>
<p>});<br>}</p>

export SMALLEST_API_KEY="your-api-key"<br>node transcribe.js recording.wav

{<br>"session_id": "sess_12345abcde",<br>"transcript": "Hello, how are you?",<br>"full_transcript": "Hello, how are you?",<br>"is_final": true,<br>"is_last": false,<br>"language": "en",<br>"words": [<br>{"word": "Hello,", "start": 0.0, "end": 0.5, "confidence": 0.98, "speaker": 0},<br>{"word": "how", "start": 0.5, "end": 0.7, "confidence": 0.99, "speaker": 0},<br>{"word": "are", "start": 0.7, "end": 0.9, "confidence": 0.97, "speaker": 0},<br>{"word": "you?", "start": 0.9, "end": 1.2, "confidence": 0.99, "speaker": 0}<br>]<br>

params = {"model": "pulse", "language": "en", "diarize": "true"}

{<br>"words": [<br>{"word": "Hello", "speaker": 0, "speaker_confidence": 0.95},<br>{"word": "Hi", "speaker": 1, "speaker_confidence": 0.92}<br>],<br>"utterances": [<br>{"text": "Hello, how can I help?", "speaker": 0},<br>{"text": "I have a question.", "speaker": 1}<br>]<br>

{<br>"emotions": {<br>"happiness": 0.28,<br>"sadness": 0.0,<br>"anger": 0.0,<br>"fear": 0.0,<br>"disgust": 0.0<br>}<br>

{<br>"transcript": "My credit card is [CREDITCARD_1] and SSN is [SSN_1]",<br>"redacted_entities": ["[CREDITCARD_1]", "[SSN_1]"]<br>

{<br>"age": "adult",<br>"gender": "female"<br>

try:<br>response = requests.post(url, params=params, headers=headers, data=audio_data, timeout=120)<br>response.raise_for_status()<br>except requests.exceptions.HTTPError as e:<br>if e.response.status_code == 429:<br># Rate limited - implement exponential backoff<br>time.sleep(2 ** retry_count)<br>elif e.response.status_code == 401:<br># Invalid API key<br>

cd demo-app<br>npm install

echo 'SMALLEST_API_KEY=your-api-key' > .env.local