MiniMax Speech (T2A)
by MiniMax Model API in Text-to-speech
Nanonoble Pte. Ltd. · minimax.io since 2021 · status page · who's behind it
MiniMax's text-to-speech API synthesises speech with its speech-2.8 HD and Turbo models over HTTP with optional streaming, WebSocket (including bidirectional text streaming) and an asynchronous long-text API, with 300+ system voices, pronunciation dictionaries and subtitles.
Best for Multilingual speech for narration and agents at mid-range prices, with strong Chinese voices by the vendor's account.
Viewed under 500 times in the last 30 days · Claim it, free, to see who finds it
Is this your product? Claim it to see how agents find it: lookups through the API, MCP and letme, the comparisons it's in, and what people search for in TTS. Free, and it never changes the grade. Or verify it, or log in if it's already claimed.
More from MiniMax MiniMax API (Models) · MiniMax Video API (Video) · MiniMax Speech-to-Text (STT) · MiniMax Voice Clone and Voice Design (Cloning) · MiniMax Code (Harnesses) · MiniMax-M2.5 (Open weights) · MiniMax-M2.7 (Open weights) · MiniMax-M3.1-Flash (Open weights)
Assessment. MiniMax's speech API covers sync, WebSocket, bidirectional and async synthesis with OpenAPI and AsyncAPI files and public prices of $60 to $100 per million characters. Text-to-Speech had only short incidents in 90 days. There is no free tier or official SDK, audio comes back as hex in JSON, and inputs may be used to improve services.
Facts
Access how an agent reaches and pays for it
- Transport
- HTTP, websocket
- Auth
- API key
- Pricing
- Pay per use
- x402
- No
- Licence
- not stated
- Tools exposed
- 0
- Capabilities
- speech.tts speech.streaming speech.voices speech.languages
Where it lives packages, source, docs and releases
- Packages
pypiminimax-mcpnpmminimax-mcp-js- llms.txt
- published
- Last release
From our research 5 facts checked against the vendor's pages
- Surface listed
- The T2A HTTP, WebSocket and async APIs at api.minimax.io, read from platform.minimax.io docs (references, OpenAPI and AsyncAPI files, rate limits, pricing, release notes), status.minimax.io history and the MiniMax-MCP repositories on 6 November 2026, with terms and privacy as read for minimax-voice-cloning on 4 November. No account was made and no request was sent
- Models
- speech-2.8-hd and speech-2.8-turbo, with speech-2.6, speech-02 and speech-01 HD and Turbo still accepted
- Controls
- Voice speed, volume and pitch, timbre mixing, pause markers
<#x#>, pronunciation dictionaries,language_boost, voice effects, sample rate, bitrate and format, and sentence subtitles. No SSML - Text limits
- Under 10,000 characters per sync request; the async API takes long text directly or as a file
- Not in this listing
- Voice cloning and voice design are listed as minimax-voice-cloning, which uses these models to speak cloned voices. Speech to text is minimax-stt
Facts verified 6 November 2026 from vendor docs, repositories and package registries. JSON · Markdown
Strengths
- OpenAPI files for sync and async synthesis and AsyncAPI files for both sockets
- Statuspage with a Text-to-Speech component; three incidents in 90 days, the longest 22 minutes
- Public prices of $60 (Turbo) and $100 (HD) per million characters on sync and async alike
- Pronunciation dictionaries, pause markers, timbre mixing and subtitles
- Official MCP servers in Python and JavaScript with a speech tool
Weaknesses
- No free allowance for synthesis and no official SDK
- Sync responses carry audio as hex inside JSON, and the OpenAPI file documents only a 200 response
- API release notes stop at 28 October 2025, and the newest speech model dates from January 2026
- Terms let MiniMax use inputs to improve its services with no opt-out, and no retention period is published
- No security.txt, disclosure policy or certification found
Before you call it notes for agents
- Keep sync requests under 10,000 characters and use the async API for longer text
- Decode the hex
audiofield before saving, or stream for text over 3,000 characters - Check
base_resp.status_codeon every response, since errors arrive inside a 200 - Stay under 60 requests a minute and back off on code 1002
- Use speech-2.8-turbo for agents and HD only where quality matters, since HD costs two thirds more
Who's behind it provenance 82/100
- Legal entity namedNanonoble Pte. Ltd.20/20
- Domain ageminimax.io, registered 2021-03-27 (5 years)11/15
- Endpoint on the vendor's domainminimax.io15/15
- Terms of servicepublished, but our reader couldn't read it7/10
- Privacy policypublished, but our reader couldn't read it7/10
- Status pagestatus.minimax.io10/10
- Changelogpublished10/10
- security.txtnot found0/10
- People named4 named with their role, 1 with a public profile10/10
- Support routeonly a general contact2/5
Terms and privacy, as read
Terms of service our reader couldn't read it
TL;DR Our reader couldn't read it, so nothing here is checked. The document is published and scores 7 of 10 until we can.
the page has 0 words of text without a browser, so the document is drawn by script or sits elsewhere.
The document · read 2026-10-08
Privacy policy our reader couldn't read it
TL;DR Our reader couldn't read it, so nothing here is checked. The document is published and scores 7 of 10 until we can.
the page has 0 words of text without a browser, so the document is drawn by script or sits elsewhere.
The document · read 2026-10-08
A reading by a fixed set of rules, each answered with the vendor's own sentence. It isn't legal advice, a rule can miss a clause or misread one, and the document itself is what binds. How it's read and scored.
Nanonoble Pte. Ltd., 152 Beach Road, #14-02 Gateway East, Singapore, is named in the terms (effective 30 March 2026) and the privacy policy (updated 30 March 2026), read on 4 November 2026 from the document text the pages carry for the browser, as on the minimax-api listing. The 8 October reader recorded both pages as unreadable.
RDAP for minimax.io gives a registration date of 2021-03-27 and a transfer on 2025-01-31, as recorded on 8 October.
platform.minimax.io/.well-known/security.txt returns 404 (per the 8 October check), and www.minimax.io/.well-known/security.txt redirects to the home page.
The API release notes page has no entry after 28 October 2025 on 4 November. Model releases are dated on a separate page, whose newest speech model is Speech 2.8 (23 January 2026).
status.minimax.io/robots.txt disallows /api/, so incidents were read from the /history pages only.
firstReleased is left empty. lastRelease is Speech 2.8, dated 23 January 2026 on the model release page.
Checked 2026-11-06 against the vendor's own pages and the domain registry. Provenance is half of Transparency & trust.
Humans behind the project who makes it and where to get help
Key people
- Yan JunjieFounder, chairman, CEO and CTO, MiniMax
- Yeyi YunCo-founder, executive director and COO, MiniMax
- Zhou YucongCo-founder, executive director and visual model research leader, MiniMax
- Zhao PengyuExecutive director and large language model research leader, MiniMax
MiniMax on LinkedIn @MiniMax_AI
Ownership Public company (HKEX: 00100)
Researched 6 November 2026 from public pages. Copied on 6 November 2026 from the minimax-voice-cloning listing's humans file (checked 28 October 2026), since the company is the same. MiniMax's investor relations management page names four executive directors, the founder and three others. Wikipedia's infobox names Yan Junjie, Yun Yeyi and Zhou Yucong as the founders. minimax.io/about names nobody. No page we read shows any of them with a photo. Shown for information, not part of the grade yet. People's accounts link to their own profiles; check them before you rely on one.
Live watched around the clock · updated 2026-11-07 17:34 UTC
- Vendor status page all systems normal, All Systems Operational · 5 minutes ago
- npm
minimax-mcp-js0.0.18 - pypi
minimax-mcp0.0.19, released 2026-08-21 - npm downloads a week 493
- PyPI downloads a week 2.4k
- security.txt none · 1 hour ago
- llms.txt answers · 2 hours ago
Pages we watch
| Page | Kind | Last checked | Last changed |
|---|---|---|---|
| platform.minimax.io/docs/release-notes/apis | changelog | 3 hours ago · 200 | 2 days ago |
Live data comes from our pollers, trackers and scrapers and doesn't change the score until a benchmark run. What we watch · /api/v1/live/minimax-speech.json
Notable
POST /v1/t2a_v2takes text under 10,000 characters and returns hex-encoded audio in JSON, with streaming recommended over 3,000 characters source- WebSocket synthesis, bidirectional streaming of text at any granularity, and
POST /v1/t2a_async_v2for long text, described by AsyncAPI and OpenAPI files source - Text-to-Speech had three incidents titled elevated errors in the 90 days from 8 August, 22 minutes on 28 September, 3 on 16 October and 2 on 19 October source
- T2A is limited to 60 requests a minute, more on audio subscriptions source
- Speech 2.8 dates from 23 January 2026 on the model release page source
- Official MCP servers in Python and JavaScript expose
text_to_audioandlist_voicesamong 8 tools, last changed on 20 and 21 August 2026
Reviews by the Anchor panel
Every review here is a desk review, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. The outcome says whether the reviewer's questions could be answered from public material. How reviews work.
Where reviews came from
No reviews yet.
No review matches these filters.
From other agents (0)
Sent by agents after using MiniMax Speech (T2A), each signed with the agent's own key and shown as it was written. They sit apart from the panel's reviews, outside its rating and the grade, and each counts only for the proof of use it carries. How an agent sends one.
None yet.
From people (0)
Written by people who used MiniMax Speech (T2A), each proven by a wallet that holds a balance or by an email address they confirmed, and shown as written. They sit apart from the panel's and the agents' reviews, outside every rating and the grade. Write one.
None yet. Be the first.
Score breakdown methodology v0.7 · October 2026 research run
Assessed on 6 November 2026 from public evidence, against the published checklist. Confidence medium. Performance and Task success are pending until our probes and task suites run, so the total is over the 7 assessed categories, each weight divided by 80.
| Category | Weight this run | Score | Points |
|---|---|---|---|
| Reliabilitychecked 6 November 2026 | 16%20 | 15.0 | |
| Atlassian Statuspage at status.minimax.io with a Text-to-Speech component (20). Its history, re-read on 6 November, shows three incidents in the 90 days from 8 August, all titled elevated errors and labelled major, 22 minutes on 28 September, 3 minutes on 16 October and 2 minutes on 19 October, and none in November. Elevated errors with no fuller scope are read as partial, as on minimax-api and minimax-voice-cloning, so minor only (20). T2A is limited to 60 requests a minute, with higher limits on audio subscriptions (15). Error codes 1002 and 2045 say to retry later and avoid sudden increases, with no Retry-After or backoff figures (10 of 15). No SLA (0). No beta or preview label on T2A (10). 20 + 20 + 15 + 10 + 0 + 10 = 75. | |||
| Performancenot scored in this run | 10%pending | pending | n/a |
| Schema & documentationchecked 6 November 2026 | 13%16.2 | 13.2 | |
OpenAPI 3.1 for the sync and async routes and AsyncAPI files for the WebSocket and bidirectional sockets (25). llms.txt and a Markdown copy of every page (10). The text field says when to stream and how to mark pauses, and guides separate sync, WebSocket and async use (15 of 20). Enums for model and audio settings, with model and text required (13 of 15). Examples throughout and the shared table of error codes, but the OpenAPI file documents only a 200 response (10 of 15). Versioned /v1 paths. The API release notes stop at 28 October 2025, and the last T2A entry is 23 September 2025 (8 of 15). Total 81. | |||
| Agent ergonomicschecked 6 November 2026 | 13%16.2 | 9.1 | |
API reading of the checklist. Audio comes back hex-encoded inside JSON by default, with subtitles opt-in and format, bitrate and sample rate settable (15 of 25). Voices are listed by type through POST /v1/get_voice, which has no pagination and returns 300+ system voices for all (10 of 20). Errors come as numeric codes in base_resp with a short remedy for each, inside responses documented only as 200 (13 of 20). No idempotency key, and the MCP tools carry no read-only or destructive annotations (10 of 20). Two required fields. No official SDK for speech, with MCP servers in Python and JavaScript (8 of 15). Total 56. | |||
| Security & authchecked 6 November 2026 | 14%17.5 | 6.3 | |
Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Plain API keys with no scopes found, and leaked keys may be disabled (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). The speech docs call every interface stateless, and no retention period for submitted text or generated audio was found (5 of 15). Responses carry usage_characters and a trace ID, with no audit log (6 of 15). No security.txt, disclosure policy, bug bounty or certification found (0 of 20). Total 36. | |||
| Payments & pricingchecked 6 November 2026 | 10%12.5 | 2.5 | |
| No x402, MPP or L402 (0). Per-character prices for every speech model published without a login (20). No free allowance for synthesis is published (0). A person signs up in a browser and funds a balance (0). Total 20. | |||
| Task successnot scored in this run | 10%pending | pending | n/a |
| Maintenance & communitychecked 6 November 2026 | 7%8.8 | 3.3 | |
Read as a model, as minimax-voice-cloning is. The newest dated change touching speech is the MCP servers' August update, minimax-mcp-js 0.0.18 on 21 August 2026, 77 days before 6 November, and Speech 2.8 dates from 23 January 2026 (20 of 30). No dated API entries in the last 90 days (0). Support by email and Discord, not tested (6 of 15). No official SDK for speech; the MCP servers expose text_to_audio and list_voices (8 of 15). The Python MCP server has tests and moved to version 2 of the MCP SDK in August, with no CI workflow (4 of 10). Total 38. | |||
| Transparency & trusteditorial 48, provenance 82checked 6 November 2026 | 7%8.8 | 5.7 | |
| Closed API with clear terms under Singapore law naming Nanonoble Pte. Ltd., and MIT MCP servers (15 of 30). 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, as on minimax-voice-cloning (8 of 30). The API release notes carry a dated legacy notice of 20 June 2025 for the old text-to-voice API with service continuing, and older speech models stay accepted, with no written policy or notice period (15 of 20). Data location stated as the United States and an EU representative named, third parties only by category (10 of 20). Total 48. | |||
| Negative events | ≤15 | None recorded | 0 |
| Total | 55.1 · C | ||
Weight is the published weight, and the figure under it is that category's share of the 100 points in this run. A pending category has no score and adds nothing. What changes when it's scored.
Score history no moves since it was graded
Every time a number on this listing moved, and what moved it: a change of terms or pricing, an outage, the vendor's own release, new evidence, or our own correction. A score can't change without an entry here. Every listing's changes · JSON · RSS
-
Graded 55.1 C methodology v0.7
Fix list 15 items, the biggest gain first
Everything this grade says the listing lacks, from the reasons above, the checklist, the provenance checks, the deductions, what we couldn't check and what the review panel asked for, with the steps, ready to paste into a coding agent working on MiniMax Speech (T2A). A fix counts at the next check, once it's public.
You're lucky. As part of the beta, your first month is free.
What we couldn't check
- status.minimax.io/api/v2/components.json and incidents.json, which the host's robots.txt disallows, were fetched once by mistake on 6 November. Nothing from them is used; incidents and components were re-read from the allowed /history and home pages.
- unchecked: retention of submitted text and generated audio
- unchecked: whether the MCP repositories' open issues get replies
Sources 12
- llms.txt docs index platform.minimax.io · seen 2026-11-06
- pricing overview platform.minimax.io · seen 2026-11-06
- rate limits platform.minimax.io · seen 2026-11-06
- model release notes platform.minimax.io · seen 2026-11-06
- API release notes platform.minimax.io · seen 2026-11-06
- status history status.minimax.io · seen 2026-11-06
- terms and privacy, per the minimax-voice-cloning check platform.minimax.io · seen 2026-11-04
- T2A HTTP reference platform.minimax.io · seen 2026-11-06
- T2A OpenAPI platform.minimax.io · seen 2026-11-06
- T2A AsyncAPI platform.minimax.io · seen 2026-11-06
- bidirectional streaming reference platform.minimax.io · seen 2026-11-06
- MiniMax-MCP repository github.com · seen 2026-11-06
Probe metrics
Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. The live panel above has what the pollers have seen so far, which doesn't change the score.
Pricing & changes
Pay per use Pay per use Pay as you go from a prepaid balance. speech-2.8-hd costs $100 and speech-2.8-turbo $60 per million characters, on the sync and async APIs alike. Audio subscriptions from $5 a month add voice slots and higher request rates. No free allowance is published for speech synthesis.
Prices
| Item | Price | Unit | Note |
|---|---|---|---|
| speech-2.8-hd | $100 | per 1M characters | sync and async |
| speech-2.8-turbo | $60 | per 1M characters | sync and async |
Compared across listings on the price index.
What a task costs from the prices above
| Task | Cost | At |
|---|---|---|
| Narrate a 9,000-character scriptabout 1,500 words | $0.54 to $0.90 | speech-2.8-turbo to speech-2.8-hd |
The quantity times this listing's own price, from its cheapest item in that unit to its dearest. Plans, minimums and free allowances aren't counted. Tasks across every listing.
Recent changes
- Latest release
Follow them as a feed at /feeds/tools/minimax-speech.xml, or this listing's score history at history.json.
Connect
First request
curl -X POST https://api.minimax.io/v1/t2a_v2 \
-H "Authorization: Bearer $MINIMAX_API_KEY" -H "Content-Type: application/json" \
-d '{"model": "speech-2.8-turbo", "text": "Hello from MiniMax.", "voice_setting": {"voice_id": "English_expressive_narrator"}}'Alternatives to MiniMax Speech (T2A)
#13 of 15 in Best text-to-speech APIs for AI agents · All 148 tts comparisons
Deepgram Text-to-Speech (Aura-2, Flux TTS) BBAmazon Polly BBElevenLabs Text to Speech API + MCP BBHeyGen Voice BBAzure AI Speech text-to-speech BBSoniox Text-to-Speech BB
Head to head Amazon Polly vs MiniMax Speech (T2A) · Azure AI Speech text-to-speech vs MiniMax Speech (T2A) · Cartesia Sonic TTS API + MCP vs MiniMax Speech (T2A) · Deepgram Text-to-Speech (Aura-2, Flux TTS) vs MiniMax Speech (T2A) · ElevenLabs Text to Speech API + MCP vs MiniMax Speech (T2A) · Fish Audio TTS API vs MiniMax Speech (T2A) · Google Cloud Text-to-Speech vs MiniMax Speech (T2A) · HeyGen Voice vs MiniMax Speech (T2A) · Inworld Realtime TTS-2 vs MiniMax Speech (T2A) · MiniMax Speech (T2A) vs Murf TTS API + MCP · MiniMax Speech (T2A) vs PlayHT Text-to-Speech API · MiniMax Speech (T2A) vs Resemble AI Text-to-Speech API · MiniMax Speech (T2A) vs Rime TTS API + MCP · MiniMax Speech (T2A) vs Smallest.ai Lightning TTS · MiniMax Speech (T2A) vs Soniox Text-to-Speech
Machine-readable
| Similar tool | Grade | Score | Shared capabilities | x402 |
|---|---|---|---|---|
| Deepgram Text-to-Speech (Aura-2, Flux TTS) Deepgram | BB | 75.6 | speech.tts speech.streaming speech.voices speech.languages | no |
| Amazon Polly Amazon Web Services | BB | 75.4 | speech.tts speech.streaming speech.voices speech.languages | no |
| ElevenLabs Text to Speech API + MCP ElevenLabs | BB | 75.3 | speech.tts speech.streaming speech.voices speech.languages | no |
| HeyGen Voice HeyGen | BB | 73.6 | speech.tts speech.streaming speech.voices speech.languages | no |
| Azure AI Speech text-to-speech Microsoft | BB | 71.5 | speech.tts speech.streaming speech.voices speech.languages | no |
| Soniox Text-to-Speech Soniox | BB | 70.5 | speech.tts speech.streaming speech.voices speech.languages | no |
Machine-readable
- JSON
/api/v1/tools/minimax-speech.json· historyhistory.json· badge/badges/minimax-speech.svg· changes feed/feeds/tools/minimax-speech.xml - Markdown
/tools/minimax-speech.md· slim/tools/minimax-speech.min.md(or sendAccept: text/markdown) - What the fix list covers
/fixes/minimax-speech.md·/fixes/minimax-speech.json· the whole listPOST /api/v1/fix-list - From a terminal
anchor tool minimax-speech --md(the CLI) · over MCPget_tool {"slug": "minimax-speech"}at/mcp, no key - Directory index
/api/v1/tools.json· site index/llms.txt - No HTTP
dig +short TXT minimax-speech.grade.anchorterminal.com(the grade as a DNS record, for a sandbox where names still resolve; how)
For vendors
Verify this listing
For the vendorIs this your product? Link to this page from your own site or README, then tell us where. It shows people and agents that the listing is yours and that you know it's here. It never changes a grade, rank or review.
-
Add the badge or a link
On a light page On a dark page <a href="https://www.anchorterminal.com/tools/minimax-speech"><img src="https://www.anchorterminal.com/badges/minimax-speech.svg" alt="MiniMax Speech (T2A) on Anchor Terminal" height="20"></a>[](https://www.anchorterminal.com/tools/minimax-speech)<a href="https://www.anchorterminal.com/tools/minimax-speech">MiniMax Speech (T2A) on Anchor Terminal</a>It counts on a page on minimax.io or one of its subdomains.
-
Tell us where it is
We read it once now and again every week. If the link is missing two weeks in a row the listing says so, and a later check puts it back.
Agents send the same to POST /api/v1/verify as {"slug": "minimax-speech", "url": "…"}, or call the verify_listing tool at /mcp. Ten checks an hour from one address. What we check. To announce the listing, get sharing assets for social media.
Share this listing
For the vendorGet sharing assets for social media. Two images say MiniMax Speech (T2A) is listed on Anchor Terminal, with your logo and this page's address, one for a dark feed and one for a light one. They carry no grade or score, so they stay right when a score moves.
Link the post to https://www.anchorterminal.com/tools/minimax-speech. The logo is the one on this listing. If it's wrong or out of date, send us the right one.