
by AssemblyAI
AssemblyAI is a voice AI platform with APIs for speech-to-text, text-to-speech, speech understanding and LLM access. Developers use it to build voice agents, notetakers and call analytics.
APIUsage-based
Step 1: Create an account and copy your API key from the AssemblyAI dashboard.
Step 2: Pick an API: pre-recorded, streaming or synchronous speech-to-text.
Step 3: Send audio through the HTTP API or the Python or TypeScript SDK.
Step 4: Turn on extras such as speaker diarization, PII redaction or keyterms prompting.
Step 5: Pass transcripts to Speech Understanding or the LLM Gateway for summaries and analysis.
Step 6: Use webhooks in production so your server is notified when a transcript finishes.
Yes. The docs describe an MCP server that connects Claude, Cursor or any MCP client to your account to transcribe, summarize and analyze audio, and a docs MCP server so coding agents can read the live documentation.
The synchronous API transcribes audio up to 20 minutes long over HTTP in one request, with no polling or webhooks. Through the SDKs, or when uploading while recording, the limit is 120 seconds.
Yes. The site lists self-hosted inference that runs in your own VPC or on-prem, alongside managed inference on AssemblyAI's cloud.
The docs list integrations with LiveKit, Pipecat, Twilio, Langflow and others.
SonioxSoniox provides speech APIs for transcription, text to speech and real-time speech translation. It supports 60+ languages through REST and WebSocket interfaces.
Resemble AIResemble AI detects AI-generated audio, video and images and offers watermarking and identity tools. It is used for fraud prevention, meeting security and content moderation, through an API or built-in integrations.
GladiaGladia is an audio infrastructure API that transcribes speech in real time or from uploaded files and adds audio intelligence such as sentiment and entity detection. It is aimed at developers building voice products.