Now live New models for transcription and text-to-speech. AssemblyAI-STT-3.7 AssemblyAI-TTS-1

Realtime Speech-to-Text API

Real-time transcription your notetaker, agents, and captions can depend on

Record

AssemblyAI-STT-3.7-Realtime

Your transcriptions will show here...

Code

import os

import assemblyai as aai
from assemblyai.streaming.v3 import (
    RealTimeEvents,
    RealTimeParameters,
    RealTimeTranscriber,
    RealTimeTranscriberOptions,
    TurnEvent,
)


def on_turn(client: RealTimeTranscriber, event: TurnEvent):
    if event.end_of_turn:
        print(event.transcript)


client = RealTimeTranscriber(
    RealTimeTranscriberOptions(terminate_timeout=30.0),
    api_key=os.environ["ASSEMBLYAI_API_KEY"],
)
client.on(RealTimeEvents.Turn, on_turn)
client.connect(
    RealTimeParameters(
        sample_rate=16000,
        speech_model="assemblyai-stt-3-7-realtime-agent",
    )
)

try:
    client.stream(aai.extras.MicrophoneStream(sample_rate=16000))
finally:
    client.disconnect(terminate=True)
Metaview
Aircall
Bland
Granola
Apollo.io
Ashby
Siro
Calabrio
Cluely
Genio
Commure
Retell
CallRail
LiveKit
EliseAI
ClickUp
HeyGen
Metaview
Aircall
Bland
Granola
Apollo.io
Ashby
Siro
Calabrio
Cluely
Genio
Commure
Retell
CallRail
LiveKit
EliseAI
ClickUp
HeyGen
Metaview
Aircall
Bland
Granola
Apollo.io
Ashby
Siro
Calabrio
Cluely
Genio
Commure
Retell
CallRail
LiveKit
EliseAI
ClickUp
HeyGen
Metaview
Aircall
Bland
Granola
Apollo.io
Ashby
Siro
Calabrio
Cluely
Genio
Commure
Retell
CallRail
LiveKit
EliseAI
ClickUp
HeyGen
Models

Pick the model that fits your workload

Real-time transcription fast enough for voice agents, accurate enough for production.

AssemblyAI-STT-3.7-Realtime

Live conversation: meetings, calls, and captions. $0.30 per hour.

  • Speaker labels final the moment a turn ends
  • 32 languages in one stream with automatic detection
  • Key terms included
  • Best for notetakers, captions, call coaching, agent assist

AssemblyAI-STT-3.7-Realtime-Agent

Conversations with voice agents. $0.45 per hour.

  • Short replies, numbers, and entities your agent can act on
  • Background speech cut by about half
  • Low-latency end-of-turn decisions and accurate partials
  • Best for voice agents and IVR

AssemblyAI-STT-3.7-Realtime languages

32 languages in one stream, with automatic language detection

Compare features

Model
AssemblyAI-STT-3.7-Realtime Notetakers, captions, call coaching
AssemblyAI-STT-3.7-Realtime-Agent Voice agents, IVR
Price
$0.30 /hr
$0.45 /hr
Languages
32, one stream, automatic detection
32, one stream, automatic detection
Contextual prompting
400-character prompt
Keyterm prompting
Included
Included
Code-switching
Speaker labels
Final at turn end
Focuses on the primary speaker
Agent turn-taking
—
Low-latency end of turn
Medical terminology
Medical mode add-on
Medical mode add-on
HIPAA BAA
On request
On request
Unlimited concurrency
Use cases

Built for every voice workflow

Real-time transcription powers every application where you stream audio.

AI Speech-to-Text transcription in 99 languages

From Spanish to Korean, deliver accurate Voice AI in the languages your users speak.

Common questions