from sarvamai import SarvamAI
client = SarvamAI()

response = client.speech_to_text.transcribe(
    file=open("audio.wav", "rb"),
    model="saaras:v3",
    mode="transcribe"
)
print(response.transcript)

import { SarvamAIClient } from "sarvamai";
import * as fs from "fs";

const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY" });

const response = await client.speechToText.transcribe({
    file: fs.createReadStream("audio.wav"),
    model: "saaras:v3",
    mode: "transcribe"
});
console.log(response.transcript);

job = client.speech_to_text_job.create_job(
    model="saaras:v3",
    mode="transcribe",
    language_code="hi-IN",
    with_diarization=True,
    num_speakers=2
)
job.upload_files(file_paths=["meeting.mp3"])
job.start()
job.wait_until_complete()
job.download_outputs(output_dir="./output")

import asyncio, base64
from sarvamai import AsyncSarvamAI

async def stream_audio():
    client = AsyncSarvamAI()
    async with client.speech_to_text_streaming.connect(
        model="saaras:v3",
        high_vad_sensitivity=True,
        flush_signal=True
    ) as ws:
        with open("audio.wav", "rb") as f:
            audio_base64 = base64.b64encode(f.read()).decode("utf-8")
        await ws.transcribe(audio=audio_base64, encoding="audio/wav", sample_rate=16000)
        await ws.flush()
        response = await ws.recv()
        print(response)

asyncio.run(stream_audio())