MiniMax Speech-to-Text vs Soniox Speech-to-Text

MiniMax Speech-to-Text 6

Read as a model. No dated release or change of asr-1.0 was found on the model or API release notes or the status page (0). No dated ASR entries in the last 90 days (0). Support by email and Discord, not tested (6 of 15). No official SDK, and the MCP servers have no transcription tool (0 of 15). No package to judge (0 of 10). Total 6.

Soniox Speech-to-Text 75

Read on the model lines the other Soniox listings use (recency 30, dated releases 10, notice 10, support 15, issues 10, SDKs 15, health 10), where the 1 October note used the tool lines. stt-rt-v6 and stt-async-v6 released on 3 November 2026, with Python SDK 2.11.0 (agent text input on RealtimeSTTConfig) and soniox-js v2026.11.03 ("Feat/v6 support") the same day (30). Since 6 August, the releases that touch STT code are Python 2.9.0 (11 August, async STT and files), 2.10.0 (2 October, realtime STT authentication), 2.11.0, soniox-js v2026.10.12 (12 October, realtime STT authentication) and v2026.11.03, plus the v6 model entry (10). For notice, the v5 models are removed on 15 December 2026, 42 days after the notice, with requests routed to v6, and WebSocket api_key authentication ends on 15 January 2027 with a migration guide; v4 had 14 days (5). A community and support page, with no reply times read (5). SDK issues unread, github.com 403 (3). Current Python and Node SDKs (15). soniox-js runs CI (.github/workflows/ci.yml), the Python repository has tests and uv.lock but no CI workflow (7). 30+10+5+5+3+15+7 = 75.

MiniMax Speech-to-Text 33

Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Plain API keys from the console with no scopes found, and the docs say publicly leaked keys may be disabled, as on minimax-voice-cloning (20 of 30). The terms (effective 30 March 2026), as read for minimax-voice-cloning on 4 November, let MiniMax use input and generated content to operate, maintain, develop and improve its services, with no opt-out found, and the privacy policy rules out only training to profile or target consumers (5 of 20). No retention period for uploaded audio or transcripts was found (3 of 15). Each response carries a trace ID, with no audit log found (5 of 15). No security.txt, disclosure policy, bug bounty or certification found, as on the other MiniMax listings (0 of 20). Total 33.

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.

MiniMax Speech-to-Text 47

Atlassian Statuspage at status.minimax.io with component history, but its components are LLM, Text-to-Speech and Video Generation, with none for speech to text (10 of 20). With no component, the history holds no record for transcription (5). Limits published with numbers, 2 concurrent connections and 30,000 audio seconds a minute (15). 429 is documented as rate_limit_error, and the general error code page says to retry later, with no backoff figures or Retry-After (7 of 15). No SLA in the terms or docs (0). asr-1.0 is called the current public model with no beta label (10). 10 + 5 + 15 + 7 + 0 + 10 = 47.

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.

MiniMax Speech-to-Text 63

Closed API with clear terms under Singapore law naming Nanonoble Pte. Ltd., as on the other MiniMax listings (15 of 30). The terms and privacy policy agree that inputs may be used to improve services and that data sits in a United States data centre, with no retention period for audio (8 of 30). No deprecation notice or policy touches the ASR API (10 of 20, for the dated notices elsewhere on the API release notes). Data location stated as the United States and an EU representative named, with third parties only by category (10 of 20). Total 43.

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).