Free APIVision & SpeechAPI keyOfficial
Gladia
Recurring 10 free hours of transcription every month, no card, all features on
Gladia provides audio infrastructure for speech-to-text built on a Whisper-derived stack, with async batch and real-time streaming, speaker diarization, translation and word-level timestamps. It targets multilingual and code-switching audio. The free tier recurs monthly with the full feature set enabled.
Free tier
Free tier: 10 hours/month, no card; then Starter ~$0.61/hr async, ~$0.75/hr real-time (volume discounts at Growth)Rate limits
Free-tier concurrency not published; usage capped by the 10h monthly allowanceAuth
API keyBase URL
https://api.gladia.ioWhat you'd build with it
- Transcribe multilingual or code-switching audio and evaluate WER on the free tier
- Add diarized, timestamped transcripts to a media pipeline
- Real-time streaming captions for a voice automation
Key endpoints
- POST
/v2/uploadUpload an audio file and get a hosted URL - POST
/v2/pre-recordedStart async transcription of an audio URL, returns a result id and result_url - GET
/v2/pre-recorded/{id}Poll a transcription job for the final result
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-textaudiotranscriptiondiarizationmultilingual