> ## Documentation Index
> Fetch the complete documentation index at: https://docs.60db.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Release notes for the 60db platform — APIs, SDKs, CLI, MCP server, and WebSocket protocol.

Every product surface shares this page. Dated entries flag the surfaces they touched (REST, WebSocket, SDK, CLI, MCP, Proxy) so you can skim by what you integrate with.

<Update label="2026-07-03" description="TTS REST — Inworld payload alignment (POST /tts-synthesize)">
  ## Changed

  **`POST /tts-synthesize` now accepts the full Inworld schema.**

  * `audio_config: { audio_encoding, sample_rate_hertz }` — nested block matching the upstream schema.
  * `timestamp_type` (default `"WORD"`) — enables per-word timestamps in the final NDJSON chunk.
  * Legacy flat keys (`sample_rate`, `audio_encoding`) still work; new clients should use `audio_config`.

  Default `sample_rate_hertz` moved from **48000 → 24000** to match the upstream default and reduce bandwidth. Callers that need 48 kHz must send it explicitly.

  See [Text to Speech reference](/api-reference/tts/text-to-speech).
</Update>

<Update label="2026-07-03" description="STT WebSocket — remove_fillers config key">
  ## Added

  **`config.remove_fillers` on WebSocket `start` (STT).**

  * New boolean field inside `start.config`. Default `false`.
  * When `true` **and** `context` is set (LLM refinement gate is open), the canonical `transcription` emit (`speech_final: true`) drops filler words — `um`, `uh`, `like`, `you know`, …
  * No effect when `context` is omitted (refinement stays off).
  * The 60db `/ws/stt` proxy coerces non-boolean values to `false` rather than rejecting the session.

  See [WebSocket STT reference](/api-reference/websocket/stt#config-remove-fillers).
</Update>

<Update label="2026-06-25" description="Onboarding, email delivery (Cloudflare), and platform fixes">
  Surfaces: **REST**, **Email**

  ## Added

  **Onboarding fields (`POST /user/onboarding`).**

  * Now accepts `default_voice_id` (string), `marketing_consent` (boolean), `consent_timestamp`, and `consent_source` — all optional and backward compatible.
  * Marketing consent is **server-stamped**: `consent_timestamp` / `consent_source` are set on the server; any client-sent values are ignored.
  * Consent is persisted **best-effort after the onboarding commit**, so a consent-write failure can never fail the onboarding save.

  **One-click unsubscribe (`/unsubscribe`).**

  * Public, HMAC-token-verified endpoint for lifecycle email. Sends a `List-Unsubscribe` (one-click) header for bulk-sender compliance.

  ## Changed

  **Email delivery now uses Cloudflare Email Service.**

  * Transactional and lifecycle mail send via Cloudflare (`smtp.mx.cloudflare.net`, implicit TLS on 465) authenticated with a Cloudflare API token; DKIM/ARC are applied automatically. Configure `CLOUDFLARE_API_TOKEN` (used as the SMTP password) and `SMTP_EMAIL` (a sender on a domain onboarded for Email Sending).
  * Signup verification email is now sent **after** the account is committed, so a transient email/transport failure can no longer roll back account creation.

  ## Fixed

  **`GET /workspaces` duplicate rows.**

  * A workspace with more than one active membership row no longer appears multiple times in the response; the list is de-duplicated per workspace.

  **Onboarding 500 on consent.**

  * Submitting onboarding no longer returns `500` when the marketing-consent columns are absent from the database (consent persistence is best-effort — apply the consent migration to enable it).

  **Email credential safety.**

  * SMTP / Cloudflare credentials are scrubbed from any thrown or logged email error.

  ## Security

  * Cerbos authorization checks added across additional routes (STT, TTS, SLM, Studio, webhooks, sixtydb).

  ## Migrations

  * New environments must apply the consent columns on `users` (`marketing_consent`, `consent_timestamp`, `consent_source`); plus the events / lifecycle-email tables if the lifecycle email program is enabled.
</Update>

<Update label="2026-06-23" description="STT editor: transcribe API + audio playback">
  Surfaces: **REST**

  ## Added

  * New STT transcribe API powering the STT editor.
  * Audio playback in the STT editor.

  ## Fixed

  * Resolved an audio-URL leak.
  * Fixed audio not playing after a redirect.
</Update>

<Update label="2026-06-06" description="Coupons for wallet top-ups">
  Surfaces: **REST**, **Billing**

  ## Added

  * **Coupon system** for wallet top-ups — percentage / fixed discounts and deposit multipliers (e.g. 2× / 3×). Redemptions are recorded for audit (`coupon_redemptions`, referencing the top-up's `payment_transaction_id`).
</Update>

<Update label="2026-04-30" description="STT/TTS reliability + new features">
  ## Added

  **Longer request timeout (REST `POST /stt`).**

  * Server-side request timeout raised from 120 s → **600 s**; clients should match. The 25 MB / \~1-hour file-size cap remains.

  **Custom vocabulary boost.**

  * New `keywords` form field on `POST /stt`. CSV with optional per-term weights, e.g. `Acme:5,XYZ Pharma:8`.
  * The same boost runs on the WebSocket path via the existing `context.terms` field — no client change required to benefit; existing `terms` payloads now produce `boosted` / `original` markers automatically.
  * Words replaced by the boost appear in the response with `boosted: true` and `original: "<pre-boost word>"`.

  **Word-level timestamps and confidence.**

  * `return_timestamps=word` adds per-word `start` / `end` to the REST response.
  * `include_confidence=true` adds per-word `confidence` (0-1).

  **Diarization controls.**

  * `min_speakers` / `max_speakers` form fields on `POST /stt`.

  **Script correction.**

  * `script_correction=true` for code-mixed Devanagari / Latin audio.

  **Audio quality indicator.**

  * `snr_db` is now a top-level field on every STT response and a per-message field on WS `transcription` events. Surface as a "good / fair / poor" badge (`>= 15` good, `0–15` fair, `< 0` poor).

  ## Limits

  **Per-user concurrency cap.** Counted across REST + WS combined.

  | Service | Default |
  | ------- | ------- |
  | STT     | 8       |
  | TTS     | 5       |

  Excess returns:

  * **REST** — `429` with `error_code: STT_CONCURRENCY_LIMIT` / `TTS_CONCURRENCY_LIMIT` and `details.limit`.
  * **WebSocket** — error frame followed by close code `1008`. The cap releases when an in-flight request completes; no server-side queueing.

  ## New error codes

  | Status | `error_code`                                      | When                                    | Retry guidance                            |
  | ------ | ------------------------------------------------- | --------------------------------------- | ----------------------------------------- |
  | 429    | `STT_CONCURRENCY_LIMIT` / `TTS_CONCURRENCY_LIMIT` | Per-user concurrency cap                | Retry after an in-flight request finishes |
  | 429    | `STT_UPSTREAM_RATE_LIMIT`                         | Upstream rate-limit pass-through        | Honor the **`Retry-After`** HTTP header   |
  | 499    | `STT_CLIENT_CANCELLED`                            | Client closed the connection mid-flight | Intentional; no retry, no charge          |
  | 503    | `STT_UPSTREAM_UNAVAILABLE`                        | Upstream STT 5xx                        | Exponential backoff                       |

  `499` is non-standard but used (nginx convention) to signal the client closed the connection before the response was sent.

  ## New warning codes

  | Code                         | Meaning                                                                                                                                                  |
  | ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
  | `low_snr_dropped`            | Audio dropped before LID/ASR; SNR below floor. Response `text` is empty. **No credits charged.**                                                         |
  | `llm_refinement_not_in_plan` | The `context` field was provided but the active plan does not include LLM refinement. The field was ignored; transcription proceeded without refinement. |

  The same `low_snr_dropped` value appears as a `processing_mode` on WS `transcription` events — treat as "skip this utterance, no useful text".

  ## Billing changes

  * **WS double-bill fix.** Sessions that previously double-billed when the client sent `stop` are now billed correctly. `billing_summary.total_duration_seconds` will show as \~50 % of historical values for affected sessions.
  * **`billing_summary.client_estimated_seconds` (new, diagnostic)** — rough estimate of audio the client sent. Useful only for debugging duration drift; never display as a billed number.
  * **Low-SNR refunds.** REST sessions where upstream dropped audio for low SNR no longer charge the user. WS already handled this.
  * **Cancellation propagation.** Client disconnects mid-request now correctly abort the upstream call. **No charge for cancelled requests** (`499 STT_CLIENT_CANCELLED`).
  * **Diarization surcharge documented.** When `diarize=true`, requests incur a documented **+30 %** surcharge on top of the base STT rate to cover GPU diarization (pyannote).

  ## Plan-tier gate

  `context` (LLM refinement) is now a paid feature. On the **Free** plan the field is silently stripped server-side and the response includes `warning_codes: ["llm_refinement_not_in_plan"]`. Surface an upgrade prompt or hide / disable the input on Free plans for better UX.

  ## Surface summary

  * **REST** — `POST /stt` accepts new form fields (`keywords`, `languages`, `min_speakers`, `max_speakers`, `return_timestamps`, `include_confidence`, `script_correction`, `min_split_sec`); returns new fields (`snr_db`, `language_source: "long_audio_chunked"`, per-word `boosted`/`original`/`confidence`, per-segment `chunk_idx`).
  * **REST `POST /tts`, `/tts-synthesize`, `/tts-stream`** — may now return `429 TTS_CONCURRENCY_LIMIT`.
  * **WebSocket `/ws/stt`** — adds `low_snr_dropped` to `processing_mode`; per-word `boosted`/`original`; message-level `snr_db`; concurrency-limit error frame + close `1008`; corrected `billing_summary` with new `client_estimated_seconds` field.
  * **WebSocket `/ws/tts`** — concurrency-limit error frame (legacy `{error: {message, code, details}}` shape) + close `1008`.
  * **Web UI** — axios timeout raised to 600 s, error-code-aware toasts, `warning_codes` surfaced, WS `1008` distinguished from auth/network failures. The 25 MB upload cap is unchanged.
</Update>

<Update label="2026-04-14" description="LLM context refinement for STT">
  ## Added — Context-gated LLM refinement

  Speech-to-Text now accepts an optional **context hint** that opens a server-side LLM refinement gate. When supplied, the response transcript is polished for proper-noun accuracy, filler removal, punctuation, and script consistency in mixed-language audio.

  The shape differs per transport:

  | Transport                                   | `context` shape                            | Enables                           |
  | ------------------------------------------- | ------------------------------------------ | --------------------------------- |
  | **REST** `POST /stt` (and `/v1/transcribe`) | plain `string` — free-form paragraph       | LLM refinement of response `text` |
  | **WebSocket** `/v1/stream` (and `/ws/stt`)  | structured object `{general, text, terms}` | Two-phase canonical final flow    |

  ### REST — `context: string`

  Free-form paragraph describing the session (domain, speakers, jargon). Serialized as a multipart form field.

  ```bash cURL theme={null}
  curl -X POST https://api.60db.ai/stt \
    -H "Authorization: Bearer $API_KEY" \
    -F "file=@meeting.wav" \
    -F "context=Cricket coaching session. Players: Arjun Mehta, Ishaan Verma. Discussing batting technique, stamina, running between wickets."
  ```

  ```javascript JavaScript theme={null}
  await client.speechToText(file, {
    language: "auto",
    diarize: true,
    context: "Cricket coaching session. Players: Arjun Mehta, Ishaan Verma.",
  });
  ```

  ```python Python theme={null}
  client.speech_to_text(
      audio_file,
      language='auto',
      diarize=True,
      context='Cricket coaching session. Players: Arjun Mehta, Ishaan Verma.',
  )
  ```

  ```bash CLI theme={null}
  60db stt:transcribe --file meeting.wav \
    --context "Cricket coaching session. Players: Arjun Mehta, Ishaan Verma."
  ```

  ```json MCP theme={null}
  {
    "audio_url": "https://example.com/meeting.wav",
    "context": "Cricket coaching session. Players: Arjun Mehta, Ishaan Verma."
  }
  ```

  ### WebSocket — structured `{general, text, terms}`

  ```json Start message theme={null}
  {
    "type": "start",
    "languages": ["en", "hi"],
    "context": {
      "general": [
        { "key": "domain", "value": "Cricket coaching" },
        {
          "key": "players",
          "value": "Arjun Mehta, Ishaan Verma, Aryan Khan, Rohan"
        }
      ],
      "text": "Coach reviewing a batting practice session.",
      "terms": ["Arjun Mehta", "Ishaan Verma", "off-side", "stamina", "wickets"]
    },
    "config": {
      "encoding": "linear",
      "sample_rate": 48000,
      "continuous_mode": true
    }
  }
  ```

  ## Changed — WebSocket two-phase canonical flow

  When `context` is supplied, each utterance now produces **two** `transcription` events sharing a `sentence_id`:

  1. **First emit** — `is_final: true, speech_final: false` — fast dict-corrected text. Use for low-latency UI paint and voicebot barge-in / NLU.
  2. **Canonical** — `is_final: true, speech_final: true` — definitive answer. Either LLM-refined (when `llm_applied: true`) or the original text re-emitted (when LLM was skipped or failed).

  New canonical-only fields:

  | Field            | Type      | Description                                                                           |
  | ---------------- | --------- | ------------------------------------------------------------------------------------- |
  | `llm_applied`    | `boolean` | `true` if the LLM ran, `false` if skipped / failed.                                   |
  | `llm_latency_ms` | `number`  | Round-trip to the LLM endpoint (SLA monitoring).                                      |
  | `llm_reason`     | `string`  | Diagnostic when `llm_applied: false` (`gate_closed`, `error:TimeoutException`, etc.). |

  Simple consumers can gate exclusively on `speech_final: true` and ignore the rest — one canonical event per utterance regardless of whether refinement is on.

  See the [WebSocket STT Reference](/api-reference/websocket/stt#canonical-answer-semantics-speech-final) for the full table and reconciliation patterns.

  ## Added — Word-preservation guardrails (proxy + UI)

  To defend against over-aggressive LLM refinement and fast-speech hallucination rejection:

  * **Refined word-retention guardrail.** If the canonical text drops more than \~60% of the first-emit's token count, the proxy rolls back to the first-emit text and marks `llm_applied: false, llm_reason: "dropped_too_many_words"`. Tuned so legitimate polish (filler removal, 10–40% compression) passes through untouched.
  * **Hallucination-rejected fallback.** When the upstream server's word-rate guard emits an empty final (`processing_mode: "hallucination_rejected"`, common on fast-paced Indic/English mixed audio), the proxy upgrades it into a tentative canonical using the cached first-emit / last-interim text plus `tentative: true` and `tentative_reason: "hallucination_rejected"` so words never silently disappear.

  Both guardrails run in the `/ws/stt` proxy, so voicebots and web clients inherit them automatically.

  ## Added — Backward-compat `refined` event handling

  Pre-migration upstream builds emit LLM refinement as a separate `refined` event rather than a second `transcription`. The proxy and web client transparently accept both shapes, so existing integrations keep working through the rollout.

  <Note>
    If you see `refined` events in the wire trace, upstream workers haven't been
    restarted onto the two-phase build yet — it's still fully functional; the
    `refined` event is deprecated but accepted.
  </Note>

  ## Surface summary

  * **REST** — `POST /stt`, `POST /v1/transcribe` — `context: string` form field.
  * **WebSocket** — `/v1/stream`, `/ws/stt` — `context: {general, text, terms}` on `start`; two-phase canonical flow; `llm_applied` / `llm_latency_ms` / `llm_reason` on canonical.
  * **JavaScript SDK** — `client.speechToText(audio, { context })`.
  * **Python SDK** — `client.speech_to_text(audio_file, context=...)`.
  * **CLI** — `60db stt:transcribe --context "..."`.
  * **MCP Server** — `sixtydb_stt_transcribe` accepts `context`.
  * **Proxy** — word-retention guardrail, hallucination fallback, first-emit caching, legacy `refined` shim.
  * **Web UI** — context input in Speech-to-Text page and realtime demo; segments rendered with `tentative` marker when flagged.

  ## Environment knobs (server-side)

  | Variable                   | Default     | Purpose                                                                     |
  | -------------------------- | ----------- | --------------------------------------------------------------------------- |
  | `STT_LLM_ENABLED`          | `true`      | Master kill-switch for refinement.                                          |
  | `STT_LLM_MODEL`            | `60db-tiny` | OpenAI-compatible model identifier.                                         |
  | `STT_LLM_TIMEOUT_SEC`      | `10.0`      | Per-call timeout — on timeout, canonical falls back to original.            |
  | `STT_LLM_MIN_WORDS`        | `4`         | Skip refinement for tiny utterances (`"Yeah"`, `"Okay"`).                   |
  | `STT_WS_HALLUCINATION_WPS` | `8.0`       | Word-rate ceiling; finals above it are flagged as `hallucination_rejected`. |
</Update>