Speech to text, $0.0015 a minute

What it does

• File transcription: POST /v1/listen with base64 audio (wav, mp3, m4a, ogg, flac, webm; 1 KB to 4.5 MB per request).
• Live transcription: WebSocket with automatic end-of-speech detection; the final text arrives about 0.8 seconds after speech stops in our test (one observation, not a guarantee).
• Billing: per second of audio, listed at $0.0015 per minute.

What it does not do yet

No speaker labels and no word timestamps. Long recordings must be sent in pieces. We have not published an accuracy benchmark; test it on your own audio.

Example

curl -X POST https://speakvora.com/api/v1/listen -H "x-api-key: $SPEAKVORA_KEY" -H "content-type: application/json" \
  -d "{\"audio_base64\":\"$(base64 < clip.wav | tr -d '\n')\",\"format\":\"wav\",\"language\":\"en\"}"

# 200 {"text":"...","seconds":3,"language":"en"}

Speed

Measured transcription times for 4 and 15 second clips are on the speed page, with the method. They are our measurements, not guarantees.

Price in native units

Sources and checked date on the (checked 2026-10-08). Models differ in accuracy, languages and features, so this is a price comparison only.