Real-time Audio Streaming
Transcribe live audio streams in real-time with low latency. Perfect for live events, phone calls, video conferences, and broadcasts in African languages.
In Development
Real-time streaming is currently in development and will be released in Q1 2026. This page provides a preview of the upcoming API and features.
Want early access? Contact us to join the beta program.
Planned Features
⚡ Low Latency
Get transcription results in under 300ms from when audio is sent.
- • Sub-second response time
- • Optimized for African languages
- • Global edge network
🔄 Interim Results
Receive partial transcriptions before the sentence is complete.
- • Progressive word updates
- • Confidence scores
- • Automatic corrections
🎙️ Multi-speaker
Real-time speaker identification and diarization.
- • Automatic speaker detection
- • Speaker labeling
- • Turn-taking analysis
🌐 WebSocket Support
Persistent bi-directional connection for streaming audio.
- • Automatic reconnection
- • Audio chunking
- • Connection health monitoring
Stream from Microphone (Preview)
Here's what the API will look like when released:
Preview Only
WebSocket Connection
import orbitalsai# Initialize streaming clientstream = orbitalsai.StreamingClient(api_key="your_api_key")# Connect to streaming endpointawait stream.connect( language="hausa", interim_results=True, enable_diarization=True)# Handle incoming transcripts@stream.on("transcript")def handle_transcript(result): if result.is_final: print(f"Final: {result.text}") else: print(f"Interim: {result.text}")# Start streaming audioawait stream.start()# Send audio chunksfor chunk in audio_stream: await stream.send_audio(chunk)# Close connectionawait stream.close()Planned Streaming Options
| Parameter | Type | Default | Description |
|---|---|---|---|
language | string | auto | Target language for transcription |
interim_results | boolean | false | Receive partial results before sentence completion |
sample_rate | integer | 16000 | Audio sample rate in Hz (8000-48000) |
enable_diarization | boolean | false | Enable real-time speaker identification |
punctuation | boolean | true | Automatically add punctuation |
Streaming Use Cases
📞 Call Center Transcription
Real-time transcription of customer service calls in African languages for quality assurance, training, and compliance.
🎥 Live Event Captioning
Provide live captions for conferences, webinars, and broadcasts in real-time, making content accessible to broader audiences.
💬 Virtual Meeting Assistants
Create AI assistants that transcribe and summarize virtual meetings in real-time, capturing action items and key decisions.
🗣️ Voice Assistants
Build voice-controlled applications with low-latency speech recognition for African language speakers.
Planned Pricing
Streaming transcription will be priced based on audio duration, similar to pre-recorded transcription.
Expected pricing: $0.10 per minute of audio streamed
Pricing subject to change before release
Get Early Access
Be among the first to try real-time streaming when it launches. Join our beta program to get early access and help shape the final product.