@mindstudio-ai/agent 0.1.122 → 0.1.123

package/dist/index.d.ts

@@ -8109,6 +8109,39 @@ interface TranscribeAudioStepInput {
 interface TranscribeAudioStepOutput {
     /** The transcribed text from the audio file */
     text: string;
+    /** Timed passages with per-segment confidence, speaker attribution and optional word-level detail — see the step's usage notes for which models populate it. Absent for models that return nothing but text. */
+    segments?: {
+        /** Seconds from the start of the audio. */
+        start: number;
+        end: number;
+        /** The passage, spacing normalized. */
+        text: string;
+        /**
+     * How sure the model was, always `0..1` with higher meaning more confident — whatever the provider reported.
+     *
+     * Normalizing this is the whole point of the type. Providers disagree on both the scale and the direction: Deepgram reports a probability in `0..1`, ElevenLabs and Whisper report a log probability in `(-inf, 0]`. Handing those through untouched would make `confidence < 0.5` mean opposite things depending on which model the caller happened to pick. Log probabilities are converted with `Math.exp`; probabilities pass through.
+     */
+        confidence?: number;
+        /** Present only when diarization was asked for and the provider supports it. */
+        speaker?: string;
+        /** Present only for providers that report language per passage rather than per request. Most report it once for the whole audio — see `TranscriptionResponse.language`. */
+        language?: string;
+        /** Word-level detail, when the caller asked for it (`includeWordTimings`). Off by default: an hour of speech is roughly ten thousand words, an order of magnitude more payload than the segments that contain them. */
+        words?: {
+            text: string;
+            /** Seconds from the start of the audio. */
+            start?: number;
+            end?: number;
+            /** See the confidence convention on `TranscriptSegment`. */
+            confidence?: number;
+            /** Provider-assigned speaker id, present only when diarization was asked for. */
+            speaker?: string;
+        }[];
+    }[];
+    /** Detected or declared language of the audio, when the model reports it. */
+    language?: string;
+    /** Length of the transcribed audio, when the model reports it. */
+    durationSeconds?: number;
 }
 interface TrimMediaStepInput {
     /** URL of the source audio or video file to trim */
@@ -11304,6 +11337,12 @@ interface StepMethods {
      *
      * @remarks
      * - The prompt field provides optional context to improve transcription accuracy (e.g. language, speaker names, domain).
+     * - Detail beyond the plain transcript is requested through `transcriptionModelOverride.config`, and support varies by model:
+     * - `includeSpeakers: 'yes'` — label each passage with a speaker. Supported by elevenlabs-scribe-v1, elevenlabs-scribe-v2, deepgram-nova-3 and grok-stt. Also switches `text` to a timestamped, speaker-labelled block format.
+     * - `includeWordTimings: 'yes'` — add per-word timings and confidence inside each segment. Supported by elevenlabs-scribe-v1, elevenlabs-scribe-v2, deepgram-nova-3 and whisper-1. Off by default because an hour of speech is roughly ten thousand words.
+     * - `detectLanguage: 'yes'` — detect the spoken language instead of assuming English (deepgram-nova-3 only; Scribe and the whisper models always report it).
+     * - The `segments` output carries timings, confidence and speakers as structured data, so there is no need to slice the audio up to recover them. It is populated for elevenlabs-scribe-v1/v2, deepgram-nova-3, whisper-1 and the DeepInfra-served whisper/voxtral/qwen models, and absent for models that return nothing but text (gpt-transcribe, gpt-4o-transcribe, grok-stt).
+     * - `confidence` is always 0..1 with higher meaning more confident, whichever model produced it.
      *
      * @example
      * ```typescript
@@ -11821,6 +11860,11 @@ declare function runWithContext<T>(ctx: RequestContext, fn: () => T | Promise<T>
  * is spend per object. The mapper's `map` runs under a per-object timeout
  * (declared in `mindstudio.json`, default 30 s); the executor never throws.
  *
+ * On a job, mapping is its own stage: the mapper turns each object into
+ * documents, and the platform ingests those documents in parallel batches of
+ * fifty across its workers, whatever one object became. An object's size does
+ * not set the pace; the number of objects sets how wide the mapping runs.
+ *
  * Declared in `mindstudio.json`:
  * ```json
  * "dataSources": [{ "slug": "archive", "mapper": { "path": "dist/datasources/archive.mapper.ts" } }]

package/dist/index.js

@@ -4421,9 +4421,9 @@ var stepMetadata = {
   "transcribeAudio": {
     stepType: "transcribeAudio",
     description: "Convert an audio file to text using a transcription model.",
-    usageNotes: "- The prompt field provides optional context to improve transcription accuracy (e.g. language, speaker names, domain).",
+    usageNotes: "- The prompt field provides optional context to improve transcription accuracy (e.g. language, speaker names, domain).\n- Detail beyond the plain transcript is requested through `transcriptionModelOverride.config`, and support varies by model:\n  - `includeSpeakers: 'yes'` \u2014 label each passage with a speaker. Supported by elevenlabs-scribe-v1, elevenlabs-scribe-v2, deepgram-nova-3 and grok-stt. Also switches `text` to a timestamped, speaker-labelled block format.\n  - `includeWordTimings: 'yes'` \u2014 add per-word timings and confidence inside each segment. Supported by elevenlabs-scribe-v1, elevenlabs-scribe-v2, deepgram-nova-3 and whisper-1. Off by default because an hour of speech is roughly ten thousand words.\n  - `detectLanguage: 'yes'` \u2014 detect the spoken language instead of assuming English (deepgram-nova-3 only; Scribe and the whisper models always report it).\n- The `segments` output carries timings, confidence and speakers as structured data, so there is no need to slice the audio up to recover them. It is populated for elevenlabs-scribe-v1/v2, deepgram-nova-3, whisper-1 and the DeepInfra-served whisper/voxtral/qwen models, and absent for models that return nothing but text (gpt-transcribe, gpt-4o-transcribe, grok-stt).\n- `confidence` is always 0..1 with higher meaning more confident, whichever model produced it.",
     inputSchema: { "type": "object", "properties": { "audioUrl": { "type": "string", "description": "URL of the audio file to transcribe" }, "prompt": { "type": "string", "description": "Optional context to improve transcription accuracy (e.g. language, speaker names, domain terms)" }, "transcriptionModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Audio transcription model identifier" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default transcription model if not specified" } }, "required": ["audioUrl", "prompt"] },
-    outputSchema: { "type": "object", "properties": { "text": { "type": "string", "description": "The transcribed text from the audio file" } }, "required": ["text"] }
+    outputSchema: { "type": "object", "properties": { "text": { "type": "string", "description": "The transcribed text from the audio file" }, "segments": { "type": "array", "items": { "type": "object", "properties": { "start": { "type": "number", "description": "Seconds from the start of the audio." }, "end": { "type": "number" }, "text": { "type": "string", "description": "The passage, spacing normalized." }, "confidence": { "type": "number", "description": "How sure the model was, always `0..1` with higher meaning more confident \u2014 whatever the provider reported.\n\nNormalizing this is the whole point of the type. Providers disagree on both the scale and the direction: Deepgram reports a probability in `0..1`, ElevenLabs and Whisper report a log probability in `(-inf, 0]`. Handing those through untouched would make `confidence < 0.5` mean opposite things depending on which model the caller happened to pick. Log probabilities are converted with `Math.exp`; probabilities pass through." }, "speaker": { "type": "string", "description": "Present only when diarization was asked for and the provider supports it." }, "language": { "type": "string", "description": "Present only for providers that report language per passage rather than per request. Most report it once for the whole audio \u2014 see `TranscriptionResponse.language`." }, "words": { "type": "array", "items": { "type": "object", "properties": { "text": { "type": "string" }, "start": { "type": "number", "description": "Seconds from the start of the audio." }, "end": { "type": "number" }, "confidence": { "type": "number", "description": "See the confidence convention on `TranscriptSegment`." }, "speaker": { "type": "string", "description": "Provider-assigned speaker id, present only when diarization was asked for." } }, "required": ["text"], "description": "One recognized token.\n\n`text` rather than `word` because an entry is not always a word \u2014 providers emit punctuation, spacing and non-speech audio events (laughter, footsteps) through the same channel." }, "description": "Word-level detail, when the caller asked for it (`includeWordTimings`). Off by default: an hour of speech is roughly ten thousand words, an order of magnitude more payload than the segments that contain them." } }, "required": ["start", "end", "text"], "description": "A contiguous passage of one speaker's speech, bounded in time.\n\nThe unit a review UI works in: short enough to seek to and highlight, coarse enough that an hour of audio is a few hundred entries rather than ten thousand." }, "description": "Timed passages with per-segment confidence, speaker attribution and optional word-level detail \u2014 see the step's usage notes for which models populate it. Absent for models that return nothing but text." }, "language": { "type": "string", "description": "Detected or declared language of the audio, when the model reports it." }, "durationSeconds": { "type": "number", "description": "Length of the transcribed audio, when the model reports it." } }, "required": ["text"] }
   },
   "trimMedia": {
     stepType: "trimMedia",