Dev, web & IT
Design, code, host and ship sites and internal tools, with an AI coding agent doing most of the typing.
Speech-to-text (STT) APIs turn audio into text, either streamed live or from recorded files. Deepgram offers streaming and batch transcription plus Flux, a model with built-in end-of-turn detection for voice agents. Use STT for dictation, call transcription, captions and voice assistants.
A speech-to-text API accepts audio and returns a transcript, often with timestamps, punctuation and speaker labels. Streaming APIs return text while someone is still talking. Batch APIs process recordings.
Streaming: open a WebSocket, send small audio chunks, and receive interim and final transcripts. Deepgram’s Flux model also emits turn events for voice agents (see turn detection).
Batch: upload a file or URL and get the full transcript back.
Accuracy helpers: formatting (punctuation, numerals) and keyterm prompting to bias recognition toward names and jargon.
Buy instead of build: Wispr Flow is system-wide dictation that cleans up your speech as it types, in supported text fields and applications. The US Pro card-billed plan is $15 per user per month on monthly billing ($144 annually); region and store terms can differ. Its developer API requires an approved organization.
Local alternatives: open models such as Whisper can run on your own hardware. Verify that the surrounding app, tools and telemetry do not transmit audio before treating the complete setup as local.
Pricing (checked 2026-10-17). Deepgram gives $200 of free credit, then bills per minute. Streaming Nova-3 is listed at $0.0048 a minute and Flux English at $0.0065 a minute on pay as you go. Both are promotional rates, with regular prices of $0.0077 a minute. Budget on the regular rate and check extra feature charges, audio-channel billing and the chosen streaming or recorded model.
Hands-free input (dictation) and searchable records of calls and meetings.
The foundation for voice agents. See the Jarvis build guide.
Consent and disclosure. With cloud STT, audio leaves the device. Tell people and get consent to record.
Accuracy varies. It can vary with noise, speakers, language and jargon, so test representative audio and inspect critical names and numbers.
Promotional prices end. Per-minute rates vary by model and plan, so re-check before you budget.
Snapshot from official sources on Oct 17, 2026.
| Deepgram streaming, pay as you go (checked 2026-10-17) | Flux English $0.0065/min (promotional; regular $0.0077); Nova-3 Monolingual $0.0048/min (promotional; regular $0.0077) [4] |
| Deepgram free credit | $200, then pay as you go [4] |
| Nova languages | 45+ languages, with diarization, smart formatting, keyterm prompting and language detection [4] |
| Flux | Streaming model with built-in turn detection for voice agents [2] |
Design, code, host and ship sites and internal tools, with an AI coding agent doing most of the typing.
Answer faster from a help desk your agent can search, with help-center drafts a person approves.
| Tool in this entry | How agents connect |
|---|---|
| Deepgram | MCPAPI/CLIFile import |
| ElevenLabs | MCPAPI/CLIFile import |
| Wispr Flow | MCPAPI/CLIFile import |
Levels come from each tool's recorded, sourced compatibility. How the levels work.
Practitioner views are restated in our words and labeled as views, not measured results. Product facts come from official sources dated above.
IonBin's wiki isn't user-edited. Corrections go to our Directory Curator, who checks them against primary sources before anything changes. Spot something wrong or out of date on “Speech-to-text APIs”? Email us with a link to a primary source.
Suggest an edit by email or write to contact@ionbin.com
ElevenLabs is a trademark of its owner. IonBin is an independent publisher and is not affiliated with, sponsored by, or endorsed by ElevenLabs. Product names are used for identification and review purposes only.