Pricing
Pay for what you send.
No seats, no monthly minimum, no credits that expire. $5 on signup, no card.
| Model | Rate |
|---|---|
| Text to speech — per 1M characters | |
echo-turbo Lowest latency, voice agents | $8 /1M |
echo-1 The default. Balanced. | $15 /1M |
echo-pro Most expressive, narration | $40 /1M |
| Speech to text — per minute of audio | |
scribe-turbo Realtime, telephony | $0.006 /min |
scribe-1 Diarisation, word timestamps | $0.012 /min |
test keys Deterministic, zero GPU | Free |
✓ billed per second, rounded up✓ cache hits at 20%✓ $5 on signup, no card✓ credit never expires
Estimate
What it would cost you.
Rough monthly figure. Cache hits are excluded, so a real bill usually comes in under this.
Text to speech
Speech to text
Estimated monthly
$31.50
synthesis $7.50
transcription $24.00
How billing works
| Unit | Characters for synthesis, seconds for transcription |
| Rounding | Up, once per request |
| Cache hits | 20% of rate — identical requests are not re-synthesised |
| Test keys | Free, always. No GPU, no wallet debit |
| Out of credit | 402 before the job runs, with the exact shortfall |
| Expiry | Credit never expires |
| Invoicing | Prepaid wallet. Annual invoicing on request |