Deepgram Text-to-Speech (Aura-2, Flux TTS) by Deepgram

# Fix list: Deepgram Text-to-Speech (Aura-2, Flux TTS)

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/deepgram-tts, the October 2026 research run, assessed 1 October 2026. Grade BB, 73 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Deepgram Text-to-Speech (Aura-2, Flux TTS): work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Per-1,000-character prices for Flux TTS, Aura-2 and Aura-1 published without a login (20). $200 credit with no card (20). A person signs up in a browser to get the first key (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 2. Reliability, 70 out of 100, up to 6 more on the total

Why it scored 70: Statuspage at status.deepgram.com with component history and an RSS feed back to May 2026 (20). Two TTS incidents in the last 90 days. Elevated Flux TTS 1011 errors on the global endpoint from 09:45 to 13:44 UTC on 25 September, which we count as one major, and 503s on some Aura-2 English voices for 40 minutes on 22 September. An AWS us-west-2 event caused intermittent errors across products for about 65 minutes on 24 July (10). TTS concurrency published per plan and region, 15 REST and 45 streaming on pay as you go, and Flux TTS only 5 in the EU, Australia and India (15). Rate-limit breaches return 429 and the docs ask for exponential backoff (15). The pricing page lists Standard Uptime on paid plans, but we found no SLA document or figure (0). Aura-2 is GA, and Flux TTS is priced, on the status page and carries no preview label in the cloud docs we read (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 3. Security & auth, 70 out of 100, up to 5.3 more on the total

Why it scored 70: Model reading of the checklist, with training and retention in place of least-privilege and injection lines. Keys belong to a project, carry a role and scopes, and browser JWTs live 30 seconds (30). Requests fall under the Model Improvement Program, which covers TTS, unless each request sets `mip_opt_out=true` (10 of 20). Opted-out requests are kept only for processing, so zero retention is self-serve but not the default (10 of 15). Per-request logs through `GET /v1/projects/{project_id}/requests`, no audit log of key actions found (10 of 15). SOC 2 Type 1 and Type 2, HIPAA with a BAA on request and PCI listed on the compliance page. No security.txt, disclosure policy or bug bounty found (10 of 20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 82 out of 100, up to 2.9 more on the total

Why it scored 82: API reading of the checklist. Encoding, container, sample rate and bit rate are all chosen per request, streaming returns PCM, mu-law or A-law and batch adds MP3, Opus, FLAC and AAC. Word timestamps on Flux only (20 of 25). Aura-2 REST caps a request at 2,000 characters and answers 413 above it, and the request history endpoint pages and filters by date, status and endpoint (20). Documented error codes, an `INPUT_MARKUP_STRIPPED` warning when SSML is dropped, and Flux's Interrupt event returns what was spoken and what wasn't (17 of 20). Backoff guidance for 429. No idempotency key, and we found nothing on billing for failed calls (10 of 20). `/v1/speak` needs only the text, and official SDKs ship in Python, JavaScript, Go, .NET and Java (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Maintenance & community, 73 out of 100, up to 2.4 more on the total

Why it scored 73: Read as a model. Changelog entries on 30 September and 1 October 2026, the latter adding watermarking to Flux TTS on self-hosted (30). More than 30 dated entries in the last 90 days (10). We found no deprecation policy and no TTS deprecation notices in the period (0 of 10). Public changelog and community support channels (10 of 15). The Python SDK has 27 open issues, the newest from August 2026 with no maintainer reply visible (3 of 10). Official SDKs current in five languages (15). SDK CI not checked (5 of 10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 6. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 60, provenance 90.

Why it scored 75: Closed service with clear terms, SDKs MIT (15). The docs describe training by default under the Model Improvement Program and EU, Australian and Indian endpoints, while the privacy policy (26 October 2021) says data sits on US servers and doesn't mention the program (15 of 30). Breaking corrections are flagged in the changelog, but we found no deprecation policy (10 of 20). Sub-processor list and four regional endpoints (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- security.txt: not found (0 of 10)

## 7. Schema & documentation, 95 out of 100, up to 0.8 more on the total

Why it scored 95: OpenAPI 3.1 file at developers.deepgram.com/openapi.json and an AsyncAPI file for the sockets (25). llms.txt and Markdown pages (10). The docs say to use Flux TTS for live agents that need barge-in and Aura-2 for other languages, though few options say when not to use them (15). `/v1/speak` has an `encoding` enum and a default model, `/v2/speak` requires `model`, and both are typed in the spec (15). Examples on each endpoint, a general errors page and a TTS troubleshooting page for WebSocket close codes such as NET-1000 (15). Versioned `/v1` and `/v2` paths and a changelog with entries most weekdays (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- Whether failed or interrupted TTS requests are billed.
- Whether the Standard Uptime on the pricing page refers to a written SLA.
- Whether a security.txt or vulnerability disclosure policy exists elsewhere on deepgram.com.

## Weaknesses

- Requests can be kept for training unless each one sets `mip_opt_out=true`
- Flux TTS is English only and capped at 5 concurrent streams in the EU, Australia and India below Enterprise
- No SSML, and Flux TTS strips other vendors' tags with a warning
- Elevated Flux TTS errors for about four hours on 25 September 2026
- Aura-2 REST requests stop at 2,000 characters

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Set `mip_opt_out=true` on every request if the text mustn't be kept for training.
- Split Aura-2 REST text under 2,000 characters or expect a 413.
- Pass `model` on `/v2/speak`, where it's required.
- Strip SSML before sending, since it's removed with an `INPUT_MARKUP_STRIPPED` warning.
- Back off exponentially on 429 and keep traffic in one project.

## What the review panel asked for

- State billing for interrupted requests
- Publish the Standard Uptime terms
- State whether failed calls bill

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.