Best speech-to-text APIs for calls
APIs that turn phone audio into text, live or after the call, compared on the rate per minute each vendor posts.
Want to see it first? Book a demo
Deepgram wins on price for live English call transcripts: its Nova-3 model has the lowest rate per minute checked here, with more volume discounts on its Growth tier. AssemblyAI wins if you want live and recorded audio priced on one page, with the widest menu of add-ons, such as speaker labels and PII redaction, billed on top.
The short answer
- Deepgram's Nova-3 model transcribes at a promotional rate of $0.0048/minute (regular $0.0077/minute) for English, with $200 in free credit on signup, per deepgram.com/pricing.
- AssemblyAI prices live and recorded audio apart. Its Universal-Streaming model is $0.15/hour ($0.0025/minute), and its recorded Universal-2 model is also $0.15/hour. You get $50 free credit and no card at signup, per assemblyai.com/pricing.
- Every rate per minute here covers the transcript only. None of it covers the language model that reads it, the voice that answers back, or the phone line that carries the call.
Speech-to-text APIs compared
| Provider | Real-time price | Free credit | Add-ons | Best for | Not for |
|---|---|---|---|---|---|
| Deepgram | $0.0048-$0.0078/min (Nova-3, Flux, promotional) | $200 | Growth tier prepaid volume discount up to 20% | Lowest cost English transcription at real volume | A team that wants one flat, unpromoted rate with no tiering |
| AssemblyAI | $0.15/hr streaming (Universal-Streaming), $0.15-$0.21/hr pre-recorded | $50, no card at signup | Diarization, medical mode, keyterm prompting, all billed separately | A team that wants transcription and add-ons documented on one clear page | A team that only needs bare transcription and doesn't want add-on line items |
| Google Cloud Speech-to-Text | Pricing on request via the interactive calculator | Google Cloud free-tier credit (general, not STT-specific) | Chirp/enhanced models, speaker diarization, custom models | A team already billing everything through Google Cloud | A team that wants a rate it can read without opening a calculator |
Figures checked on deepgram.com/pricing and assemblyai.com/pricing, September 2026. Google Cloud's speech-to-text pricing page renders its rate table through an interactive calculator rather than a static price list, so no flat per-minute figure is quoted here; the vendor's own pricing page is cloud.google.com/speech-to-text/pricing.
How the three differ in practice
Deepgram
Built around a family of named models (Nova-3, Flux) rather than one flat rate, with monolingual English pricing lower than multilingual detection. The current promotional rates are meaningfully below the vendor's own listed regular rates, so a rate quoted today is not guaranteed to hold at renewal. Not for: a team that wants price certainty without checking back after a promotional period ends.
AssemblyAI
Bills real-time streaming by WebSocket session duration (open-to-close time), not by the audio actually sent, which means a call left connected but silent still accrues cost. Its add-on menu, from PII redaction to medical-mode vocabulary, is itemized and stacks additively on top of the base rate rather than bundled into a single higher tier. Not for: a team that wants one number covering everything with no line items to track.
Google Cloud Speech-to-Text
Priced through Google Cloud's standard consumption model, billed in second increments of audio processed, with standard and enhanced or Chirp-family model tiers. The pricing page itself does not render as a static table; the rate depends on model, region and audio type selected in an interactive calculator, which makes it harder to quote a single number with confidence. Not for: comparing costs quickly without stepping through the calculator first.
How to choose
Choose Deepgram if you need the lowest rate for live English calls. Choose AssemblyAI if you want live and recorded audio on one price page with a wide add-on menu. Choose Google Cloud Speech-to-Text if your stack already runs on Google Cloud. If you'd rather buy a finished voice agent, a platform like Vapi or Retell AI already bundles a speech-to-text provider into its rate per minute.
Disclosure: SalesCrew is our product. It runs outbound calls through Vapi as one channel and logs each outcome on the contact record. Voicemails are transcribed and sit in the inbox thread list beside the call log (see SalesCrew phone).
Questions
- What does speech-to-text for a phone call actually cost?
- The posted rate per minute covers only the transcript. A live voice agent also pays for the phone line, a language model to read the transcript, and a voice to answer back. So speech-to-text is often the smallest of the four costs, not the total.
- Is streaming transcription more expensive than transcribing a recording afterward?
- Yes, most of the time. AssemblyAI prices live streaming apart from recorded audio. Its streaming tiers cost more per hour than its after-the-fact models, since the service must hold a line open and send words back fast, not work on a finished file.
- Do I need a paid plan to test one of these?
- No. Deepgram gives new accounts $200 in free credit and AssemblyAI gives $50, both usable against real usage with no card at signup, per each vendor's own pricing page.
- Which one is cheapest for a high-volume call center?
- On the rates checked here, Deepgram's Nova-3 models cost the least per minute for English. Its Growth tier cuts the price more if you prepay for a year. AssemblyAI's after-the-fact model holds its own for calls you transcribe once they end.