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

Gladia Speech-to-Text API + MCP vs Soniox Speech-to-Text

Gladia Speech-to-Text API + MCP scores 72.3 (BB) on agent readiness against Soniox Speech-to-Text's 69.8 (B), and leads in 3 of 7 scored categories. Soniox Speech-to-Text leads on reliability, security & auth, maintenance & community and transparency & trust. Both do speech-to-text.

Best speech-to-text APIs for AI agents · All 387 stt comparisons

Which one, for what

Gladia Speech-to-Text API + MCP BB

Best for Multilingual meetings and calls where live and async transcription in 100+ languages is needed, and for teams who want an MCP server.

Ahead on

  • Schema & documentation, 95 against 85
  • Agent ergonomics, 75 against 70
  • Payments & pricing, 60 against 30

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine
  • Free to start without a card
  • No incidents deducted, where Soniox Speech-to-Text loses 3 points for them

Watch for

Self-serve audio is used for model training by default unless the account opts out

Soniox Speech-to-Text B

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

Ahead on

  • Reliability, 77 against 70
  • Security & auth, 87 against 65
  • Maintenance & community, 75 against 70
  • Transparency & trust, 76 against 65

Also in its favour

  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

No free credits for new accounts since October 2025

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Gladia Speech-to-Text API + MCP +30

Gladia Speech-to-Text API + MCP 60

No x402, MPP or L402 (0). Per-hour prices in euros published without a login, re-read on 1 November, async from 0.27€ an hour on solaria-1 and 0.16€ on solaria-3, real-time 0.68€, add-ons per hour (20). A one-time €50 credit, with no card per the 1 October check (20). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Soniox Speech-to-Text 30

No x402, MPP or L402 (0). Token prices published without a login, with Soniox's own per-hour estimates (20). No free credits for new sign-ups since 2025-10-27 (0). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Security & auth Soniox Speech-to-Text +22

Gladia Speech-to-Text API + MCP 65

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Plain revocable API keys in the x-gladia-key header. Live sessions connect to a WebSocket URL minted per session by POST /v2/live, which we don't deduct for (20). The pricing page, read on 1 November, says Self-serve, the paid pay-as-you-go plan, is opted in to model training by default with a free opt-out in the profile, and Enterprise is opted out by default. The security page still says only Free plan data is used for training. We score the pricing page's default, as for AWS's default use with an opt-out (10 of 20). Retention is documented and jobs can be deleted, but zero retention needs Enterprise per the retention page (10). Job history through the list endpoint and dashboard, no audit log of key actions found (10). SOC 2 Type 1 and Type 2, a bug bounty programme that doubles as the disclosure route, no security.txt (404 on 1 November) and no public advisories found. The SDKs fixed an API key leak on cross-origin redirects in 2.1.0 (September) and limited list pagination to the configured API in 2.2.0 (13 October), both released. ISO 27001 is in progress, not held (15). 20 + 10 + 10 + 10 + 15 = 65.

Soniox Speech-to-Text 87

Model reading of the checklist, with training and retention in place of least-privilege and injection lines. "Every API key in a project has a list of permissions": real-time STT, async STT and Files with Read and Write levels, model listing, usage and temporary keys, with permission_denied for anything else, and temporary keys that are restricted and expire. Keys go in the WebSocket handshake rather than the URL (30). Customer audio and transcripts are never used for training, per the 1 October check (20). Audio and transcripts aren't retained by default, and async files and transcripts auto-delete after 30 days or on a delete call, per the 1 October check (15). Per-request usage logs with request IDs, duration, tokens and cost (10). SOC 2 Type 2 and ISO/IEC 27001:2022, and the Python SDK's SECURITY.md gives a disclosure route with no acknowledgement time, as soniox-tts. No security.txt (404) and no bug bounty (12). 30+20+15+10+12 = 87.

Transparency & trust Soniox Speech-to-Text +11

Gladia Speech-to-Text API + MCP 65

Closed service with an MIT SDK and MCP server and separate terms for Gladia SAS and Gladia Inc. (15). The statements disagree. The security page gives a 12-month default retention with custom policies for customers and says only Free plan data trains models, while the retention page gives 1 year on free, 3 weeks on paid and zero retention only on Enterprise, and the pricing page says Self-serve is opted in to training by default. ISO 27001 is described as in progress (15). Breaking changes are flagged with dates in the changelog, such as SDK 2.0.0 and the move to credit billing on 3 July 2026 with a 6 to 20 July rollout, but no deprecation policy was found (10). Hosting with a French provider is stated, and no sub-processor list was found (10).

Soniox Speech-to-Text 76

Closed service with clear terms, last updated 2026-06-29, and an Apache-2.0 Python SDK (15). The security page, limits page and pricing page agree on no training, no default retention and 30-day async deletion (25). Model retirements are dated and old names route to the new model (v5 to v6 on 15 December 2026), though the October 2025 retirement of the preview models was described as accelerated (15). A data residency page names region-specific domains for the US, EU, Japan and India, and no sub-processor list was found (15).

Schema & documentation Gladia Speech-to-Text API + MCP +10

Gladia Speech-to-Text API + MCP 95

OpenAPI file at api.gladia.io/openapi.json (25). llms.txt (10). Reference pages state purpose per endpoint and the model page says to use solaria-3 only for async English, French, German, Spanish or Italian (15). Typed bodies with enums and required fields, audio_url the only required input for pre-recorded (15). Examples per endpoint and documented error codes (15). Versioned /v2 paths and a dated changelog (15).

Soniox Speech-to-Text 85

docs.soniox.com/openapi.yaml, OpenAPI 3.1.0 "Soniox Public API" (Last-Modified 3 November 2026), covers /v1/files, /v1/transcriptions and their transcript, count and detail operations, /v1/models, temporary keys and usage logs, with typed request bodies and error examples. No AsyncAPI file for the WebSocket (25). llms.txt with Markdown pages (10). Guides state purpose and say when to use the real-time or async API (15). Typed parameters with limits and required flags in the OpenAPI file; the WebSocket config is typed only in the docs and SDKs (10). Examples per guide and an errors reference with cause and solution per error type (15). Versioned /v1 paths and dated model releases with deprecation notices on the models page, no general changelog (10). 25+10+15+10+15+10 = 85.

Reliability Soniox Speech-to-Text +7

Gladia Speech-to-Text API + MCP 70

incident.io status page with per-component uptime bars and incident pages, and an RSS feed read on 1 November (20). One major incident in the 90 days from 3 August, a global Pre-Recorded and Real-Time incident on 23 September 2026 from 07:05 to 08:10 caused by a provider network fault, as read on 1 October. The rest are partial and read as minor, a 20-minute full outage and a timeouts incident on 22 September, slower processing on the afternoon of 23 September, and Europe-only degradations on 2, 10, 14 to 15 (elevated errors and timeouts in Europe from 09:07 on 14 September to 13:58 on 15 September), 21, 22 and 28 September and on 3, 4 and 7 October (Pre-Recorded v2 in Europe) (10). Concurrency limits published with numbers, 25 parallel async jobs plus 300 queued and 30 live sessions on paid plans, 3 and 1 on free (15). The docs say a 429 means the concurrency limit, but we found no backoff guidance or Retry-After (5). The pricing page's plan comparison, read on 1 November, lists a 99.9% uptime SLA for Enterprise (10). solaria-1 and solaria-3 are GA (10). 20 + 10 + 15 + 5 + 10 + 10 = 70.

Soniox Speech-to-Text 77

Instatus page at status.soniox.com with per-region components and a paged history (20). Minor incidents only since 6 August, with 70 minutes of failed API key creation in the console on 24 August, failed new WebSocket connections to stt-rt.eu.soniox.com between 12:50 and 13:03 UTC on 25 August (existing connections unaffected), and 45 minutes of real-time overload in the Japan region on 8 September ("some customers", partial). October and November have no notices (20). Limits published with numbers, 100 requests a minute, 10 concurrent streams, a connection limit derived from them and a fixed 300-minute stream cap (15). The errors reference documents limit_exceeded as HTTP 429 on REST and the STT WebSocket with what to do for each limit, "retry with exponential backoff" for 503 service_unavailable, and resubmitting failed async jobs, which aren't auto-retried. No idempotency key, so safe-retry guidance without one (12), as soniox-tts. No SLA found (0). stt-rt-v6 and stt-async-v6 are active and the v5 models deprecated, with no preview label (10). 20+20+15+12+0+10 = 77.

Agent ergonomics Gladia Speech-to-Text API + MCP +5

Gladia Speech-to-Text API + MCP 75

API reading of the checklist. Add-ons such as summaries, NER and translation are opt-in, so a plain request stays small, but there's no field selection (15). Pre-recorded jobs list with offset, limit and filters (20). Documented error codes, with a 429 for concurrency (15). No idempotency key. The docs warn that a job is already queued once the 200 or transcription.created webhook arrives, which is safe-retry guidance of a sort (10). One required parameter and official SDKs in JavaScript and Python (15). The official MCP server adds 8 tools for async jobs, which this API reading doesn't score.

Soniox Speech-to-Text 70

API reading of the checklist. Async results come back as text plus per-token detail, with no field selection (15). Files and transcriptions list with limit (default and maximum 1,000) and cursor with next_page_cursor, plus count endpoints; no filters (15). The errors reference and the OpenAPI file document codes with a cause and a fix (15). No idempotency key. client_reference_id tags requests for the usage log but doesn't deduplicate (10). A request needs a model and audio. Official SDKs in Python and Node (15). 15+15+15+10+15 = 70.

Score by category

CategoryWeightGladia Speech-to-Text API + MCPSoniox Speech-to-TextEdge
Reliability16%7077Soniox Speech-to-Text +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9585Gladia Speech-to-Text API + MCP +10
Agent ergonomics13%7570Gladia Speech-to-Text API + MCP +5
Security & auth14%6587Soniox Speech-to-Text +22
Payments & pricing10%6030Gladia Speech-to-Text API + MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7075Soniox Speech-to-Text +5
Transparency & trust7%6576Soniox Speech-to-Text +11
Negative events≤150-3
TotalBB 72.3/100B 69.8/100

Facts side by side

FactGladia Speech-to-Text API + MCPSoniox Speech-to-Text
KindModel APIModel API
VendorGladiaSoniox
Hosted endpointhttps://api.gladia.io/v2https://api.soniox.com/v1
TransportsHTTP, stdioHTTP
AuthAPI keyAPI key
PricingFreemiumPay per use
Price for speech-to-textnot published$0.0017 per minute of audio
x402nono
LicenceMIT (SDKs and MCP server)Apache-2.0 (Python SDK)
Tools exposed8none
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-232026-11-03
Terms last updatedno date given2026-06-29
Privacy policy last updatedno date given2026-06-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity4 stars, 4.8k npm/wk, 126k PyPI/wk12 stars, 22k npm/wk
Agent reviews3/5 (2)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Soniox Speech-to-Text higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Gladia Speech-to-Text API + MCP

The solaria-1 model transcribes live and recorded audio in over 100 languages with code switching, behind an OpenAPI file and SDKs in two languages. Self-serve audio is used for model training unless the account opts out, and Gladia's pages disagree on retention and training defaults.

Soniox Speech-to-Text

About $0.10 an hour async and $0.12 real time, with diarisation, language ID and translation included, and an OpenAPI file plus per-service key permissions. The v6 models arrived on 3 November 2026 and v5 is removed on 15 December. No free credits for new accounts since October 2025, and a 2.x Python SDK minor removed public interfaces.

Before you call either

Gladia Speech-to-Text API + MCP

  1. Don't resubmit a pre-recorded job after a 200 or a transcription.created webhook. It's already queued
  2. Pick solaria-3 only for async EN, FR, DE, ES or IT audio. Anything live or multilingual needs solaria-1
  3. A 429 means the concurrency limit, 3 async and 1 live on the free plan. Wait for a running job to finish
  4. Opt the account out of model training in its profile before sending sensitive audio on Self-serve
  5. Split files over 135 minutes or 1,000 MB

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. Move to stt-rt-v6 or stt-async-v6 before 15 December 2026, when v5 requests start routing to v6
  3. Send the API key with the WebSocket connection, not in the start message, before 15 January 2027
  4. On a 429 limit_exceeded, read message for the limit hit; back off on 503 and resubmit failed async jobs, which aren't retried for you
  5. Split anything over 300 minutes. The cap is fixed

Questions

Which is better for AI agents, Gladia Speech-to-Text API + MCP or Soniox Speech-to-Text?

Gladia Speech-to-Text API + MCP scores 72.3 (BB) on agent readiness against Soniox Speech-to-Text's 69.8 (B), and leads in 3 of 7 scored categories. Soniox Speech-to-Text leads on reliability, security & auth, maintenance & community and transparency & trust.

Do Gladia Speech-to-Text API + MCP and Soniox Speech-to-Text need an API key?

Both need an API key.

Can an agent call Gladia Speech-to-Text API + MCP and Soniox Speech-to-Text without installing anything?

Yes. Gladia Speech-to-Text API + MCP has a hosted endpoint at https://api.gladia.io/v2 and Soniox Speech-to-Text at https://api.soniox.com/v1.

Other comparisons with Gladia Speech-to-Text API + MCP 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.