Loli 2.0 Speech-to-Text API

curl -X POST "https://studio.evomlabs.com/api/v1/stt/transcriptions" \
  -H "Authorization: Bearer stt_sk_live_YOUR_KEY" \
  -F "audio=@recording.wav" \
  -F "language=auto"

import requests

with open("recording.wav", "rb") as audio:
    response = requests.post(
        "https://studio.evomlabs.com/api/v1/stt/transcriptions",
        headers={"Authorization": "Bearer stt_sk_live_YOUR_KEY"},
        files={"audio": audio},
        data={"language": "auto"},
        timeout=1800,
    )

response.raise_for_status()
print(response.json()["text"])

{
  "text": "Nội dung đã phiên âm",
  "language": "vi",
  "duration_ms": 1234,
  "provider": "loli-asr",
  "model": "Loli 2.0"
}

curl -N -X POST "https://studio.evomlabs.com/api/v1/stt/transcriptions?stream=true" \
  -H "Authorization: Bearer stt_sk_live_YOUR_KEY" \
  -F "audio=@meeting.mp3" \
  -F "language=vi"

{"type":"started","duration_seconds":42.5,"chunks_total":2,"provider":"loli-asr","model":"Loli 2.0"}
{"type":"chunk","index":1,"chunks_total":2,"text":"...","combined_text":"...","language":"vi"}
{"type":"chunk","index":2,"chunks_total":2,"text":"...","combined_text":"...","language":"vi"}
{"type":"final","text":"...","language":"vi","is_final":true,"provider":"loli-asr","model":"Loli 2.0","latency_ms":5230}

{
  "type": "error",
  "error": {
    "code": "stt_upstream_error",
    "message": "Error description"
  }
}

wss://studio.evomlabs.com/api/public/v1/stt/ws?token=stt_sk_live_YOUR_KEY&language=auto

{
  "type": "start",
  "mode": "auto",
  "language": "auto",
  "sample_rate": 48000,
  "format": "pcm_s16le"
}

// Start with: { "type": "start", "mode": "manual", ... }
// Send PCM16 frames, then commit exactly that buffered speech:
ws.send(JSON.stringify({ type: "commit" }));

// The server returns one final segment. Send commit again for the next turn,
// or stop to commit a sufficiently long trailing buffer and close the session.
ws.send(JSON.stringify({ type: "stop" }));

// Server to client

{ "type": "started", "session_id": "session_id", "mode": "auto", "language": "auto",
  "sample_rate": 16000, "provider": "loli-asr", "model": "Loli 2.0" }

{ "type": "partial", "index": 0, "text": "live window text",
  "committed_text": "", "live_text": "live utterance text",
  "combined_text": "live utterance text", "is_final": false,
  "language": "vi", "latency_ms": 210 }

{ "type": "segment", "index": 0, "text": "committed utterance",
  "committed_text": "committed utterance", "live_text": "",
  "combined_text": "committed utterance", "is_final": true,
  "language": "vi", "latency_ms": 350 }

{ "type": "final", "text": "Toàn bộ transcript", "language": "vi",
  "is_final": true, "provider": "loli-asr", "model": "Loli 2.0",
  "latency_ms": 4100 }

{ "type": "closed", "session_id": "session_id", "reason": "stopped" }

{ "type": "error", "session_id": "session_id-or-null",
  "message": "Error description", "code": "bad_request" }

const ws = new WebSocket(
  "wss://studio.evomlabs.com/api/public/v1/stt/ws" +
  "?token=stt_sk_live_YOUR_KEY&language=auto"
);

ws.addEventListener("open", () => {
  ws.send(JSON.stringify({
    type: "start",
    mode: "auto",
    language: "auto",
    sample_rate: 48000,
    format: "pcm_s16le",
  }));
});

ws.addEventListener("message", (event) => {
  const message = JSON.parse(event.data);
  if (message.type === "partial" || message.type === "segment") {
    renderTranscript(message.combined_text);
  }
  if (message.type === "final") {
    renderTranscript(message.text);
  }
  if (message.type === "error") {
    console.error(message.code, message.message);
  }
});

// Send PCM16 frames with ws.send(arrayBuffer).
function stopTranscription() {
  if (ws.readyState === WebSocket.OPEN) {
    ws.send(JSON.stringify({ type: "stop" }));
  }
}