Stream audio to Wispr Flow and receive real-time transcription. Wispr specializes in developer-context-aware dictation -- it understands code terms, CLI commands, and technical jargon.
import requests, os
# Transcribe an audio file
with open("voice-memo.wav", "rb") as audio:
response = requests.post(
"https://api.wisprflow.ai/api/v1/transcribe",
headers={"Authorization": f"Bearer {os.environ['WISPR_API_KEY']}"},
files={"audio": audio},
data={"language": "en", "context": "programming"},
)
result = response.json()
print(f"Text: {result['text']}")
print(f"Confidence: {result.get('confidence', 'N/A')}")
// Stream microphone audio to Wispr Flow
const ws = new WebSocket('wss://api.wisprflow.ai/api/v1/ws');
// Browser audio capture
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
const context = new AudioContext({ sampleRate: 16000 });
const source = context.createMediaStreamSource(stream);
const processor = context.createScriptProcessor(4096, 1, 1);
source.connect(processor);
processor.connect(context.destination);
processor.onaudioprocess = (event) => {
const audioData = event.inputBuffer.getChannelData(0);
// Convert Float32Array to Int16Array for transmission
const int16 = new Int16Array(audioData.length);
for (let i = 0; i < audioData.length; i++) {
int16[i] = Math.max(-32768, Math.min(32767, audioData[i] * 32768));
}
ws.send(int16.buffer);
};
ws.onmessage = (event) => {
const data = JSON.parse(event.data);
if (data.type === 'partial') {
console.log(`Partial: ${data.text}`);
} else if (data.type === 'final') {
console.log(`Final: ${data.text}`);
}
};
Partial: implement a function that
Final: Implement a function that calculates the Fibonacci sequence using dynamic programming.
| Error | Cause | Solution |
|---|---|---|
| Garbled text | Wrong sample rate | Use 16kHz mono PCM |
| No results | Silence or noise | Check microphone input |
| High latency | REST endpoint | Use WebSocket for streaming |
Proceed to wispr-local-dev-loop for development workflow.