Speech to text API, no credit card

60 free minutes of transcription with just an account. At the limit the API stops; it never bills a card you did not add.

The short answer

Yes: 60 minutes of speech to text, free, with no credit card. Create an account, copy your key, send audio. At the limit the API stops; it never bills a card you did not add.

Try it in three steps

  1. Create an account and make an API key in the dashboard (no card is asked for).
  2. Send a recording:
    curl -X POST https://speakvora.com/api/v1/listen \
      -H "x-api-key: YOUR_KEY" -H "content-type: application/json" \
      -d "{\"audio_base64\": \"$(base64 < clip.wav | tr -d '\n')\", \"format\": \"wav\", \"language\": \"en\"}"
  3. Read the text from the text field of the response.

The same key also gets 100,000 free characters of text to speech. See text to speech with no card.

What happens at the limit

The API answers 402 free_allowance_used. Nothing is charged. Add a card in the portal to keep going: $0.0015 per minute, pay as you go.

How far 60 minutes goes

UseRoughly
Short voicemails (about 30 seconds each)120 messages
Test calls (about 3 minutes each)20 calls
One-minute voice notes60 notes

Honest limits

  • The allowance is one-time, per account.
  • No word timestamps or speaker labels yet.
  • No accuracy benchmark published: test on your own audio.

Cheapest speech to text API · pricing compared · quickstart

Questions

Is there a speech to text API with a free tier and no credit card?

Yes. Every Speakvora account gets 60 minutes of speech to text free. You create an account and make an API key; no card is asked for.

Can I get a surprise bill?

No. Without a card on the account the API cannot bill you. When the 60 free minutes are used, requests are refused with HTTP 402 and the error code free_allowance_used until you add a card.

Does the free allowance renew each month?

No. It is a one-time 60 minutes per account, not a monthly plan.

How much does it cost after the free minutes?

$0.0015 per minute of audio ($0.09 per hour), billed per second, pay as you go, no subscription and no monthly minimum.

Is the free tier limited to a worse model?

No. The free minutes use the same Whisper large-v3-turbo model as paid requests.

What are the limits?

Up to 4.5 MB of audio per request (send longer recordings in pieces), formats wav, mp3, m4a, ogg, flac and webm. No word timestamps and no speaker labels yet. We have not published an accuracy benchmark, so test on a sample of your own recordings. Audio is sent through our server to a hosted speech-recognition service to be transcribed.