Blog
Tutorials, guides, and product updates from the SpeakEasy team.
Voice Activity Detection in Python: The Complete Guide
Learn how to implement voice activity detection in Python using webrtcvad, Silero VAD, and pyannote.audio — then pipe detected speech straight into a transcription API.
Open Source Text-to-Speech in 2026
A developer's guide to the best open source TTS models in 2026 — Kokoro, Chatterbox, VibeVoice, Dia2, and Fish Audio. Where each shines, where each falls short, and when a cloud API wins.
How to Build an AI Voice Agent with a Speech-to-Text API
Voice agents need real-time STT, an LLM, and TTS working together. Here's how the architecture works, what to watch out for, and how to build one without overpaying.
The Real Cost of Speech-to-Text APIs in 2026
Speech-to-text API pricing looks simple until you add streaming, diarization, and concurrency. Here's what providers actually charge — and how to avoid overpaying.
Translate Audio to English in One API Call
Pass audio in any of 99+ languages, get back English text. No intermediate translation step, no extra API, no extra cost. Just set translate=true.
Generate SRT and VTT Subtitle Files Directly from Audio
SpeakEasy is the only affordable speech API that returns SRT and VTT subtitle files natively. No post-processing, no custom formatter — one API call.
How to Use the Prompt Parameter to Improve Whisper Transcription Accuracy
The prompt parameter lets you feed Whisper context about your audio — brand names, speaker names, technical vocabulary. Here's how to use it effectively.
Async Transcription API with Callback URLs
Learn how to transcribe long audio files asynchronously using a callback URL. Fire-and-forget transcription for podcasts, meetings, and large video files.
Python Speech-to-Text API: Transcribe Audio in 5 Lines of Code
Transcribe audio in Python using the OpenAI SDK pointed at SpeakEasy. Get transcripts with speaker labels, timestamps, and async processing in under 5 lines.
Speech-to-Text API in JavaScript: Complete Guide (2026)
The complete speech-to-text JavaScript guide — Node, browser, streaming, diarization, error handling, and production patterns. OpenAI SDK compatible via SpeakEasy.
Best Speech-to-Text APIs in 2026 Compared
We tested 8 leading speech-to-text APIs on accuracy, price, latency, and developer experience. Here's exactly what we found — with real benchmark data.
Whisper API Alternative: The Shopping Guide (2026)
A shopping-intent guide for developers replacing OpenAI Whisper. Migration checklists for Docker, CI/CD, serverless, and batch pipelines. Real cost math, not marketing.
Speaker Diarization: Identify Who Said What in Audio
Learn what speaker diarization is, why it matters, and how to use the SpeakEasy API to automatically identify speakers in audio recordings with code examples.
Build a Text-to-Speech App in 5 Minutes
Generate natural TTS audio in under 5 lines of Python via the OpenAI SDK pointed at SpeakEasy. 6 voices, streaming, HD mode, and 5 formats at $0.20/hour.
$1. 50 hours. Both STT and TTS.
Your current speech API provider is charging you too much. Switch in one line of code.