Gladia Live (Solaria-1)

Overview

Best for: Multilingual live transcription with code-switching and EU vendor preference, with optional realtime translation.

At a glance

100+ languages (Solaria-1). Free credit is EUR 50, one-time. $0.75/hr is the Starter PAYG price; Growth as low as $0.25/hr with commitment. Diarization documented for pre-recorded only. Audio and transcripts retained 3 weeks by default on paid plans.

Features

• partial transcripts
• endpointing (silence threshold and max utterance duration)
• code-switching
• custom vocabulary
• realtime translation, summarization, NER and other audio intelligence add-ons
• multi-channel tagging
• webhooks/callbacks
• recorded audio retrievable after the session

Pricing

Free tier: One-time EUR 50 credit (vendor estimates 60+ realtime hours); does not renew.

Source: gladia.io

Setup

1. Get an API key (x-gladia-key).
2. POST https://api.gladia.io/v2/live with encoding, sample_rate, bit_depth, channels and options; the response returns a session id and a WebSocket url.
3. Connect to that url (the token is embedded) and send binary audio chunks.
4. Read transcript messages (is_final flags partial vs final), send {"type":"stop_recording"} to end, then GET /v2/live/{id} for the full result.

Endpoint

POST https://api.gladia.io/v2/live, then the wss url returned in the response

Authentication

x-gladia-key header on the init POST only; the returned WebSocket URL carries its own session token, so browsers can connect without the API key.

import asyncio, json, os, requests, websockets  # pip install requests websockets>=14

cfg = {"encoding": "wav/pcm", "sample_rate": 16000, "bit_depth": 16, "channels": 1,
       "messages_config": {"receive_partial_transcripts": True}}
r = requests.post("https://api.gladia.io/v2/live", json=cfg,
                  headers={"x-gladia-key": os.environ["GLADIA_API_KEY"]})
r.raise_for_status()
ws_url = r.json()["url"]  # session-scoped, safe to hand to a browser

async def main():
    async with websockets.connect(ws_url) as ws:
        async def send():
            with open("audio_16k_mono.raw", "rb") as f:
                while chunk := f.read(3200):  # 100 ms
                    await ws.send(chunk)
                    await asyncio.sleep(0.1)
            await ws.send(json.dumps({"type": "stop_recording"}))
        asyncio.create_task(send())
        async for msg in ws:
            d = json.loads(msg)
            if d.get("type") == "transcript":
                kind = "FINAL" if d["data"]["is_final"] else "partial"
                print(kind, d["data"]["utterance"]["text"])

asyncio.run(main())

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Plus 12 warnings that apply to all speech-to-text, live APIs. See category warnings.

Limits

• Concurrent live sessions: Free 1, Paid 30 (default), Enterprise on demand; HTTP 429 when exhausted.
• A single live session cannot exceed 3 hours.
• Paid accounts can also queue up to 300 async jobs (not relevant to live).

Models and products

Docs and sources

Docs

• Pricing
• Models
• Live quickstart
• Concurrency and limits
• Data retention

Sources used

• gladia.io/pricing
• docs.gladia.io/chapters/introduction/models.md
• docs.gladia.io/chapters/limits-and-specifications/concurrency.md
• docs.gladia.io/chapters/limits-and-specifications/data-retention.md
• docs.gladia.io/chapters/live-stt/quickstart.md