@mindstudio-ai/agent 0.1.149 → 0.1.150

package/dist/index.d.ts

@@ -537,6 +537,15 @@ interface MindStudioModel {
     maxResponseSize?: number;
     /** Accepted input types for this model (text, imageUrl, videoUrl, etc.). */
     inputs?: Record<string, unknown>[];
+    /**
+     * When the platform retires this model (`YYYY-MM-DD`, from 00:00 UTC). Until
+     * then it runs as itself; from then saved calls run on `replacedBy`.
+     */
+    retiresOn?: string;
+    /** The model that runs in this one's place once it has retired. */
+    replacedBy?: string;
+    /** True once the model has retired: a call to it runs on `replacedBy`. */
+    retired?: boolean;
 }
 /** A lightweight AI model summary. */
 interface MindStudioModelSummary {
@@ -547,6 +556,15 @@ interface MindStudioModelSummary {
     type?: ModelType;
     /** Comma-separated tags for the model. */
     tags?: string;
+    /**
+     * When the platform retires this model (`YYYY-MM-DD`, from 00:00 UTC). Until
+     * then it runs as itself; from then saved calls run on `replacedBy`.
+     */
+    retiresOn?: string;
+    /** The model that runs in this one's place once it has retired. */
+    replacedBy?: string;
+    /** True once the model has retired: a call to it runs on `replacedBy`. */
+    retired?: boolean;
 }
 /**
  * Supported model type categories for filtering.
@@ -8551,6 +8569,8 @@ interface TranscribeAudioStepOutput {
     language?: string;
     /** Length of the transcribed audio, when the model reports it. */
     durationSeconds?: number;
+    /** The transcript as an SRT or WebVTT file, when `subtitles` was asked for in the model's config and the model returned segments to time it by. */
+    subtitles?: string;
 }
 interface TrimMediaStepInput {
     /** URL of the source audio or video file to trim */
@@ -11550,6 +11570,10 @@ interface StepMethods {
      *
      * @remarks
      * - The text field contains the exact words to be spoken (not instructions).
+     * - Voice, delivery and format are set through `speechModelOverride.config`, whose keys are the model's own (look a model up with its id). Delivery direction, where a model takes one, is never spoken: `styleInstruction` on gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, `instructions` on gpt-realtime-2.1-mini-tts, `voice_instruction` on seed-speech-tts-2.0, `emotion` on cartesia-sonic-3.6 and the MiniMax models.
+     * - Tags in the text act at that point, in each vendor's own syntax: `[laughs]` or `[whispers]` on elevenlabs-tts with Eleven v4 or v3; `<laugh>`, `<sigh>` or `<whispers>` on the Gemini 3.8 models; `[laugh]`, `[pause]` or `<whisper>…</whisper>` on grok-voice-tts; `[laughter]` or `<emotion value="excited"/>` on cartesia-sonic-3.6; `[be happy and upbeat]` on inworld-tts-2.
+     * - A dialogue between voices: set `$mode: 'dialogue'` and name each speaker (`speaker1_name`, `speaker1_voice`, `speaker2_name`, …), then write the text as a script, one `Name: line` per turn. Supported by elevenlabs-tts (Eleven v4 or v3, up to 4 speakers) and the Gemini 3.8 models (exactly 2).
+     * - A text longer than a model takes in one request is spoken in pieces and joined, and then comes back as MP3 whatever format was asked for.
      * - In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.
      *
      * @example
@@ -11564,12 +11588,20 @@ interface StepMethods {
      * Convert an audio file to text using a transcription model.
      *
      * @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).
+     * - The default model is elevenlabs-scribe-v2: speakers, word timings, key terms and redaction, at any length.
+     * - The prompt field gives context (speaker names, domain) to OpenAI's and DeepInfra's models. Other models ignore it; give them `keyterms` instead.
+     * - Options go in `transcriptionModelOverride.config`, and support varies by model:
+     * - `language` — the spoken language as a code such as `en` or `es`; left out, the model detects it. Every model takes it. deepgram-nova-3 assumes `en` unless told, and also takes `multi` for speech that switches language (billed at its multilingual rate).
+     * - `detectLanguage: 'yes'` — detect the language instead of assuming English (deepgram-nova-3 only).
+     * - `includeSpeakers: 'yes'` — label each passage with a speaker. Supported by elevenlabs-scribe-v2, elevenlabs-scribe-v2-medical, deepgram-nova-3, grok-stt, voxtral-mini-transcribe-2 and gemini-3.5-transcribe; gpt-4o-transcribe-diarize always does. Scribe and Voxtral also switch `text` to a timestamped, speaker-labelled block format; Deepgram, Gemini and gpt-4o-transcribe-diarize to `Speaker N:` lines.
+     * - `numSpeakers` — the most people talking, to help tell them apart (Scribe).
+     * - `keyterms` — a list of names, products and terms the audio contains, so they're spelled right. Supported by gpt-transcribe, Scribe, deepgram-nova-3, grok-stt, voxtral-mini-transcribe-2 and gemini-3.5-transcribe. Billed as an add-on on Scribe and Deepgram.
+     * - `redactPii: 'yes'` — replace names, phone numbers, addresses and other personal information with a label of what was there (Scribe, deepgram-nova-3). Billed as an add-on.
+     * - `includeWordTimings: 'yes'` — add per-word timings and confidence inside each segment. Supported by Scribe, deepgram-nova-3, whisper-1, grok-stt, voxtral-mini-transcribe-2 and gemini-3.5-transcribe. Off by default because an hour of speech is roughly ten thousand words.
+     * - `subtitles: 'srt' | 'vtt'` — also return the transcript as a subtitle file, in the `subtitles` output, timed by the segments. Any model that returns segments.
+     * - gemini-3.5-transcribe can't take `keyterms` together with speakers, word timings or subtitles, and voxtral-mini-transcribe-2 can't take `language` together with word timings or subtitles; either asked for both is refused.
+     * - 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 by Scribe, deepgram-nova-3, grok-stt, whisper-1, gpt-4o-transcribe-diarize, voxtral-mini-transcribe-2 (unless given a language), gemini-3.5-transcribe (with word timings or subtitles) and the DeepInfra-served whisper and qwen models, and absent for models that return nothing but text (gpt-transcribe, gpt-4o-transcribe, gpt-4o-mini-transcribe, the DeepInfra-served voxtral models).
+     * - A recording of any length can be transcribed. One longer than a model takes at once (OpenAI's and DeepInfra's models, Gemini) is transcribed in pieces and joined, its timings running from the start of the recording. Speakers can't be followed from one piece to the next, so with speakers on, such a recording is refused; Scribe and Deepgram label speakers at any length.
      * - `confidence` is always 0..1 with higher meaning more confident, whichever model produced it.
      *
      * @example

package/dist/index.js

@@ -5107,16 +5107,16 @@ var stepMetadata = {
   "textToSpeech": {
     stepType: "textToSpeech",
     description: "Generate an audio file from provided text using a speech model.",
-    usageNotes: "- The text field contains the exact words to be spoken (not instructions).\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
+    usageNotes: "- The text field contains the exact words to be spoken (not instructions).\n- Voice, delivery and format are set through `speechModelOverride.config`, whose keys are the model's own (look a model up with its id). Delivery direction, where a model takes one, is never spoken: `styleInstruction` on gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, `instructions` on gpt-realtime-2.1-mini-tts, `voice_instruction` on seed-speech-tts-2.0, `emotion` on cartesia-sonic-3.6 and the MiniMax models.\n- Tags in the text act at that point, in each vendor's own syntax: `[laughs]` or `[whispers]` on elevenlabs-tts with Eleven v4 or v3; `<laugh>`, `<sigh>` or `<whispers>` on the Gemini 3.8 models; `[laugh]`, `[pause]` or `<whisper>\u2026</whisper>` on grok-voice-tts; `[laughter]` or `<emotion value=\"excited\"/>` on cartesia-sonic-3.6; `[be happy and upbeat]` on inworld-tts-2.\n- A dialogue between voices: set `$mode: 'dialogue'` and name each speaker (`speaker1_name`, `speaker1_voice`, `speaker2_name`, \u2026), then write the text as a script, one `Name: line` per turn. Supported by elevenlabs-tts (Eleven v4 or v3, up to 4 speakers) and the Gemini 3.8 models (exactly 2).\n- A text longer than a model takes in one request is spoken in pieces and joined, and then comes back as MP3 whatever format was asked for.\n- In foreground mode, the audio is displayed to the user. In background mode, the URL is saved to a variable.",
     inputSchema: { "type": "object", "properties": { "text": { "type": "string", "description": "The text to convert to speech" }, "intermediateAsset": { "type": "boolean" }, "speechModelOverride": { "type": "object", "properties": { "model": { "type": "string", "description": "Speech synthesis model identifier" }, "config": { "type": "object", "properties": {}, "required": [], "description": "Additional model-specific configuration" } }, "required": ["model"], "description": "Optional model configuration override. Uses the workflow's default speech model if not specified" } }, "required": ["text"] },
     outputSchema: { "type": "object", "properties": { "audioUrl": { "type": "string", "description": "URL of the generated audio file" } }, "required": ["audioUrl"] }
   },
   "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).\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.",
+    usageNotes: "- The default model is elevenlabs-scribe-v2: speakers, word timings, key terms and redaction, at any length.\n- The prompt field gives context (speaker names, domain) to OpenAI's and DeepInfra's models. Other models ignore it; give them `keyterms` instead.\n- Options go in `transcriptionModelOverride.config`, and support varies by model:\n  - `language` \u2014 the spoken language as a code such as `en` or `es`; left out, the model detects it. Every model takes it. deepgram-nova-3 assumes `en` unless told, and also takes `multi` for speech that switches language (billed at its multilingual rate).\n  - `detectLanguage: 'yes'` \u2014 detect the language instead of assuming English (deepgram-nova-3 only).\n  - `includeSpeakers: 'yes'` \u2014 label each passage with a speaker. Supported by elevenlabs-scribe-v2, elevenlabs-scribe-v2-medical, deepgram-nova-3, grok-stt, voxtral-mini-transcribe-2 and gemini-3.5-transcribe; gpt-4o-transcribe-diarize always does. Scribe and Voxtral also switch `text` to a timestamped, speaker-labelled block format; Deepgram, Gemini and gpt-4o-transcribe-diarize to `Speaker N:` lines.\n  - `numSpeakers` \u2014 the most people talking, to help tell them apart (Scribe).\n  - `keyterms` \u2014 a list of names, products and terms the audio contains, so they're spelled right. Supported by gpt-transcribe, Scribe, deepgram-nova-3, grok-stt, voxtral-mini-transcribe-2 and gemini-3.5-transcribe. Billed as an add-on on Scribe and Deepgram.\n  - `redactPii: 'yes'` \u2014 replace names, phone numbers, addresses and other personal information with a label of what was there (Scribe, deepgram-nova-3). Billed as an add-on.\n  - `includeWordTimings: 'yes'` \u2014 add per-word timings and confidence inside each segment. Supported by Scribe, deepgram-nova-3, whisper-1, grok-stt, voxtral-mini-transcribe-2 and gemini-3.5-transcribe. Off by default because an hour of speech is roughly ten thousand words.\n  - `subtitles: 'srt' | 'vtt'` \u2014 also return the transcript as a subtitle file, in the `subtitles` output, timed by the segments. Any model that returns segments.\n- gemini-3.5-transcribe can't take `keyterms` together with speakers, word timings or subtitles, and voxtral-mini-transcribe-2 can't take `language` together with word timings or subtitles; either asked for both is refused.\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 by Scribe, deepgram-nova-3, grok-stt, whisper-1, gpt-4o-transcribe-diarize, voxtral-mini-transcribe-2 (unless given a language), gemini-3.5-transcribe (with word timings or subtitles) and the DeepInfra-served whisper and qwen models, and absent for models that return nothing but text (gpt-transcribe, gpt-4o-transcribe, gpt-4o-mini-transcribe, the DeepInfra-served voxtral models).\n- A recording of any length can be transcribed. One longer than a model takes at once (OpenAI's and DeepInfra's models, Gemini) is transcribed in pieces and joined, its timings running from the start of the recording. Speakers can't be followed from one piece to the next, so with speakers on, such a recording is refused; Scribe and Deepgram label speakers at any length.\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" }, "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"] }
+    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." }, "subtitles": { "type": "string", "description": "The transcript as an SRT or WebVTT file, when `subtitles` was asked for in the model's config and the model returned segments to time it by." } }, "required": ["text"] }
   },
   "trimMedia": {
     stepType: "trimMedia",