Speech Recognition in 2026

# Self-hosted Whisper with faster-whisper (CTranslate2 backend)
# pip install faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel("large-v3", device="cuda", compute_type="float16")

segments, info = model.transcribe(
    "meeting.wav",
    beam_size=5,
    language="en",
    vad_filter=True,           # Skip silence for faster processing
    vad_parameters=dict(
        min_silence_duration_ms=500,
    ),
)

print(f"Detected language: {info.language} (prob: {info.language_probability:.2f})")

for segment in segments:
    print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")

# Deepgram Nova-3 real-time streaming
# pip install deepgram-sdk

import asyncio
from deepgram import DeepgramClient, LiveOptions, LiveTranscriptionEvents

async def transcribe_stream():
    dg = DeepgramClient("YOUR_API_KEY")
    connection = dg.listen.asynclive.v("1")

    async def on_message(self, result, **kwargs):
        transcript = result.channel.alternatives[0].transcript
        if transcript:
            print(f"[{result.start:.2f}s] {transcript}")

    connection.on(LiveTranscriptionEvents.Transcript, on_message)

    options = LiveOptions(
        model="nova-3",
        language="en",
        smart_format=True,
        diarize=True,
        encoding="linear16",
        sample_rate=16000,
    )

    await connection.start(options)

    # Stream audio chunks from microphone or file
    with open("call_recording.wav", "rb") as f:
        while chunk := f.read(4096):
            connection.send(chunk)
            await asyncio.sleep(0.1)  # Simulate real-time

    await connection.finish()

asyncio.run(transcribe_stream())

# AssemblyAI Universal-2 with speaker diarization
# pip install assemblyai

import assemblyai as aai

aai.settings.api_key = "YOUR_API_KEY"

config = aai.TranscriptionConfig(
    speech_model=aai.SpeechModel.best,       # Universal-2
    speaker_labels=True,                       # Diarization
    auto_chapters=True,                        # Chapter summaries
    entity_detection=True,                     # PII detection
    sentiment_analysis=True,
)

transcriber = aai.Transcriber()
transcript = transcriber.transcribe("podcast_episode.mp3", config=config)

# Print with speaker labels
for utterance in transcript.utterances:
    print(f"Speaker {utterance.speaker}: {utterance.text}")

# Auto-generated chapters
for chapter in transcript.chapters:
    print(f"\n## {chapter.headline}")
    print(f"   {chapter.summary}")
    print(f"   [{chapter.start/1000:.0f}s - {chapter.end/1000:.0f}s]")

# Gemini 2.5 Pro audio transcription + analysis
# pip install google-genai

from google import genai

client = genai.Client(api_key="YOUR_API_KEY")

# Upload audio file
audio_file = client.files.upload(file="earnings_call.mp3")

# Transcribe AND analyze in one call
response = client.models.generate_content(
    model="gemini-2.5-pro",
    contents=[
        audio_file,
        """Transcribe this audio precisely, then provide:
        1. Full transcript with timestamps
        2. Key topics discussed
        3. Action items mentioned
        4. Overall sentiment per speaker""",
    ],
)

print(response.text)

# Streaming transcription via Live API
async def live_transcribe():
    async with client.aio.live.connect(
        model="gemini-2.5-pro",
        config={"response_modalities": ["TEXT"]},
    ) as session:
        # Send audio chunks for real-time transcription
        with open("live_audio.pcm", "rb") as f:
            while chunk := f.read(4096):
                await session.send_realtime_input(
                    audio={"data": chunk, "mime_type": "audio/pcm"}
                )
        response = await session.receive()
        print(response.text)