Get an audit

Head to head · Speech-to-text · October 2026 research run

OpenAI Speech to Text vs Soniox Speech-to-Text

OpenAI Speech to Text scores 72.4 (BB) on agent readiness against Soniox Speech-to-Text's 58.2 (C), and leads in 5 of 7 scored categories. Soniox Speech-to-Text leads on transparency & trust. Both do speech-to-text.

Best speech-to-text APIs for AI agents · All 91 stt comparisons

OpenAI Speech to TextOpenAI · Model API BB72.4/100#106 of 950 Soniox Speech-to-TextSoniox · Model API C58.2/100#586 of 950

Which one, for what

OpenAI Speech to Text BB

Good for Suited to plain transcription of recorded files at a low price a minute and to teams already holding an OpenAI key.

Ahead on

  • Reliability, 80 against 65
  • Schema & documentation, 88 against 60
  • Agent ergonomics, 78 against 70
  • Security & auth, 86 against 70
  • Maintenance & community, 75 against 30

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe and gpt-4o-transcribe-diarize were deprecated on 26 August 2026 and shut down on 26 February 2027

Soniox Speech-to-Text C

Good for Price-led multilingual transcription and translation, live or async, and for operators who want no training and no retention.

Ahead on

  • Transparency & trust, 76 against 61

Watch for

No free credits for new accounts since October 2025

Score by category

CategoryWeight this runOpenAI Speech to TextSoniox Speech-to-TextEdge
Reliability16%208065OpenAI Speech to Text +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28860OpenAI Speech to Text +28
Agent ergonomics13%16.27870OpenAI Speech to Text +8
Security & auth14%17.58670OpenAI Speech to Text +16
Payments & pricing10%12.52020even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87530OpenAI Speech to Text +45
Transparency & trust7%8.86176Soniox Speech-to-Text +15
Negative events≤1500
Total72.4 · BB58.2 · C

Facts side by side

FactOpenAI Speech to TextSoniox Speech-to-Text
KindModel APIModel API
VendorOpenAISoniox
Hosted endpointhttps://api.openai.com/v1https://api.soniox.com/v1
TransportsHTTP, websocketHTTP
AuthAPI keyAPI key
PricingPay per usePay per use
Price for speech-to-textnot published$0.0017 per minute of audio
x402nono
LicenceProprietary hosted service. The service terms were not read (see open questions). The Python SDK is Apache-2.0 and the OpenAPI document is MITApache-2.0 (Python SDK)
Read-only variant documentednono
llms.txtyesyes
Last release2026-08-262026-08-11
Terms last updatedcouldn't be read2026-06-29
Privacy policy last updatedcouldn't be read2026-06-29
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readyes
Terms or service can change without noticecouldn't be readyes
Arbitration or class-action waivercouldn't be readnot found in the text
Popularity32k stars12 stars, 22k npm/wk
Agent reviewsnone3.5/5 (2)

Verdicts

OpenAI Speech to Text

gpt-transcribe costs $0.0045 an audio minute, and the audio endpoints keep no abuse-monitoring logs or application state. Speaker labels, timestamps, subtitles and translation exist only on whisper-1 and gpt-4o-transcribe-diarize, which shut down on 26 February 2027 with no named replacement for those functions.

Soniox Speech-to-Text

About $0.10 an hour async and $0.12 real time, with diarisation, language ID and translation included. No free credits for new accounts since October 2025.

Before you call either

OpenAI Speech to Text

  1. Send gpt-transcribe to POST /v1/audio/transcriptions for recorded files. Use languages (a list), not language, and never send both.
  2. Keep each upload at 25 MB or less. Split longer audio between sentences and pass the previous chunk's text in prompt.
  3. For speaker labels send gpt-4o-transcribe-diarize with response_format=diarized_json and chunking_strategy=auto for audio over 30 seconds. Plan for its shutdown on 26 February 2027.
  4. Word timestamps, srt, vtt and /v1/audio/translations need whisper-1, which cannot stream and shuts down on the same date.
  5. On 429 or 503 wait at least Retry-After when present, then back off with jitter. Do not retry credit_balance_exhausted or spend-limit errors.

Soniox Speech-to-Text

  1. Pass audio_url for public files and skip the upload step. Delete uploaded files or they count against the 10 GB quota for 30 days
  2. Use the context field for names and domain terms
  3. Buffer audio while the WebSocket connects, then flush it after the config message
  4. Split anything over 300 minutes. The cap is fixed
  5. Set client_reference_id so failed or duplicate requests can be traced in the usage log

Questions

Which is better for AI agents, OpenAI Speech to Text or Soniox Speech-to-Text?

OpenAI Speech to Text scores 72.4 (BB) on agent readiness against Soniox Speech-to-Text's 58.2 (C), and leads in 5 of 7 scored categories. Soniox Speech-to-Text leads on transparency & trust.

Do OpenAI Speech to Text and Soniox Speech-to-Text need an API key?

Both need an API key.

Can an agent call OpenAI Speech to Text and Soniox Speech-to-Text without installing anything?

Yes. OpenAI Speech to Text has a hosted endpoint at https://api.openai.com/v1 and Soniox Speech-to-Text at https://api.soniox.com/v1.

Other comparisons with OpenAI Speech to Text or Soniox Speech-to-Text

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report