Free APIVision & SpeechAPI keyOfficial
AssemblyAI
$50 in free credits, no card; speech-to-text plus LeMUR LLM audio intelligence
AssemblyAI is a speech-to-text API with batch and streaming transcription plus audio intelligence add-ons: speaker diarization, entity/topic detection, summarization and the LeMUR framework for running LLM prompts over transcripts. You submit audio by URL or upload, poll the transcript id, then read the result.
Free tier
$50 one-time free credit, no card (~333 hours on Universal-2 at $0.15/hr); then pay-as-you-goRate limits
~5 concurrent transcriptions on free/PAYG; extra files queue rather than run in parallelAuth
API keyBase URL
https://api.assemblyai.comWhat you'd build with it
- Transcribe and summarize call recordings in an automation
- Run LeMUR LLM prompts ('what were the action items?') over a transcript
- Auto-detect speakers and topics for a meeting-notes Skill
Key endpoints
- POST
/v2/transcriptSubmit audio (by URL) for transcription, returns a transcript id - GET
/v2/transcript/{id}Poll a transcript by id for status and final text - POST
/v2/uploadUpload a local audio file before transcribing
Members
Members get the runnable recipe
Sign in free to copy the example request, see a sample response, and read the gotchas.
Tags
speech-to-textaudiotranscriptionllmvoice