Skip to content

Commit be604d4

Browse files
kristinaorekhovakristinaorekhova
authored
Add files via upload
1 parent 3cb8f34 commit be604d4

1 file changed

Lines changed: 359 additions & 0 deletions

File tree

‎docs/api-references/speech-models/Deepgram/nova-3-medical.json‎

Lines changed: 359 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,359 @@
1+
{
2+
"openapi": "3.0.0",
3+
"info": {
4+
"title": "AIML API",
5+
"version": "1.0.0"
6+
},
7+
"servers": [
8+
{
9+
"url": "https://api.aimlapi.com"
10+
}
11+
],
12+
"paths": {
13+
"/v1/stt/create": {
14+
"post": {
15+
"operationId": "_v1_stt_create",
16+
"requestBody": {
17+
"required": true,
18+
"content": {
19+
"application/json": {
20+
"schema": {
21+
"type": "object",
22+
"properties": {
23+
"model": {
24+
"type": "string",
25+
"enum": [
26+
"nova-3-medical"
27+
]
28+
},
29+
"url": {
30+
"type": "string",
31+
"format": "uri",
32+
"description": "URL of the input audio file. Provide either url or audio — exactly one is required, not both.",
33+
"example": "https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3"
34+
},
35+
"audio": {
36+
"type": "string",
37+
"format": "binary",
38+
"description": "The audio file to transcribe. Provide either url or audio — exactly one is required, not both."
39+
},
40+
"language": {
41+
"type": "string",
42+
"description": "The BCP-47 language tag that hints at the primary spoken language. Depending on the model and API endpoint you choose, only certain languages are available.",
43+
"example": "en"
44+
},
45+
"punctuate": {
46+
"type": "boolean",
47+
"nullable": true,
48+
"description": "Adds punctuation and capitalization to the transcript."
49+
},
50+
"smart_format": {
51+
"type": "boolean",
52+
"nullable": true,
53+
"description": "Applies formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability."
54+
},
55+
"diarize": {
56+
"type": "boolean",
57+
"nullable": true,
58+
"description": "Recognizes speaker changes. Each word in the transcript will be assigned a speaker number starting at 0."
59+
},
60+
"multichannel": {
61+
"type": "boolean",
62+
"nullable": true,
63+
"description": "Enable Multichannel transcription, can be true or false."
64+
},
65+
"paragraphs": {
66+
"type": "boolean",
67+
"nullable": true,
68+
"description": "Splits audio into paragraphs to improve transcript readability."
69+
},
70+
"utterances": {
71+
"type": "boolean",
72+
"nullable": true,
73+
"description": "Segments speech into meaningful semantic units."
74+
},
75+
"utt_split": {
76+
"type": "number",
77+
"description": "Seconds to wait before detecting a pause between words in submitted audio."
78+
},
79+
"detect_language": {
80+
"anyOf": [
81+
{
82+
"type": "array",
83+
"items": {
84+
"type": "string"
85+
}
86+
},
87+
{
88+
"type": "boolean",
89+
"nullable": true
90+
}
91+
],
92+
"description": "Enables language detection to identify the dominant language spoken in the submitted audio."
93+
},
94+
"detect_entities": {
95+
"type": "boolean",
96+
"nullable": true,
97+
"description": "When Entity Detection is enabled, the Punctuation feature will be enabled by default."
98+
},
99+
"intents": {
100+
"type": "boolean",
101+
"nullable": true,
102+
"description": "Recognizes speaker intent throughout a transcript or text."
103+
},
104+
"sentiment": {
105+
"type": "boolean",
106+
"nullable": true,
107+
"description": "Recognizes the sentiment throughout a transcript or text."
108+
},
109+
"topics": {
110+
"type": "boolean",
111+
"nullable": true,
112+
"description": "Detects topics throughout a transcript or text."
113+
},
114+
"summarize": {
115+
"anyOf": [
116+
{
117+
"type": "string"
118+
},
119+
{
120+
"type": "boolean"
121+
}
122+
],
123+
"description": "Summarizes content. For Listen API, supports string version option. For Read API, accepts boolean only."
124+
},
125+
"custom_intent": {
126+
"anyOf": [
127+
{
128+
"type": "string"
129+
},
130+
{
131+
"type": "array",
132+
"items": {
133+
"type": "string"
134+
}
135+
}
136+
],
137+
"description": "A custom intent you want the model to detect within your input audio if present. Submit up to 100."
138+
},
139+
"custom_intent_mode": {
140+
"type": "string",
141+
"enum": [
142+
"strict",
143+
"extended"
144+
],
145+
"description": "Sets how the model will interpret strings submitted to the custom_intent param. When strict, the model will only return intents submitted using the custom_intent param. When extended, the model will return its own detected intents in addition to those submitted."
146+
},
147+
"custom_topic": {
148+
"anyOf": [
149+
{
150+
"type": "string"
151+
},
152+
{
153+
"type": "array",
154+
"items": {
155+
"type": "string"
156+
}
157+
}
158+
],
159+
"description": "A custom topic you want the model to detect within your input audio if present. Submit up to 100."
160+
},
161+
"custom_topic_mode": {
162+
"type": "string",
163+
"enum": [
164+
"strict",
165+
"extended"
166+
],
167+
"description": "Sets how the model will interpret strings submitted to the custom_topic param. When strict, the model will only return topics submitted using the custom_topic param. When extended, the model will return its own detected topics in addition to those submitted."
168+
},
169+
"keyterm": {
170+
"anyOf": [
171+
{
172+
"type": "string"
173+
},
174+
{
175+
"type": "array",
176+
"items": {
177+
"type": "string"
178+
}
179+
}
180+
],
181+
"description": "Keyterm Prompting (Nova-3 Medical only): boost recognition of specialized and clinical terms, drug names, and medical proper nouns. Pass a single term or an array of terms."
182+
},
183+
"filler_words": {
184+
"type": "boolean",
185+
"nullable": true,
186+
"description": "Filler Words can help transcribe interruptions in your audio, like \"uh\" and \"um\"."
187+
},
188+
"profanity_filter": {
189+
"type": "boolean",
190+
"nullable": true,
191+
"description": "Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely."
192+
},
193+
"redact": {
194+
"anyOf": [
195+
{
196+
"type": "string"
197+
},
198+
{
199+
"type": "array",
200+
"items": {
201+
"type": "string"
202+
}
203+
}
204+
],
205+
"description": "Redact sensitive information from the transcript. Common values: pii, pci, numbers."
206+
},
207+
"replace": {
208+
"anyOf": [
209+
{
210+
"type": "string"
211+
},
212+
{
213+
"type": "array",
214+
"items": {
215+
"type": "string"
216+
}
217+
}
218+
],
219+
"description": "Search for terms and replace them in the transcript. Provide \"find:replace\" pairs."
220+
},
221+
"search": {
222+
"anyOf": [
223+
{
224+
"type": "string"
225+
},
226+
{
227+
"type": "array",
228+
"items": {
229+
"type": "string"
230+
}
231+
}
232+
],
233+
"description": "Search for terms or phrases in submitted audio."
234+
},
235+
"dictation": {
236+
"type": "boolean",
237+
"nullable": true,
238+
"description": "Identifies and extracts key entities from content in submitted audio."
239+
},
240+
"measurements": {
241+
"type": "boolean",
242+
"nullable": true,
243+
"description": "Spoken measurements will be converted to their corresponding abbreviations."
244+
},
245+
"numerals": {
246+
"type": "boolean",
247+
"nullable": true,
248+
"description": "Numerals converts numbers from written format to numerical format."
249+
},
250+
"encoding": {
251+
"type": "string",
252+
"enum": [
253+
"linear16",
254+
"flac",
255+
"mulaw",
256+
"amr-nb",
257+
"amr-wb",
258+
"opus",
259+
"speex",
260+
"g729"
261+
],
262+
"description": "Expected encoding of the submitted audio (used mainly for raw audio)."
263+
},
264+
"tag": {
265+
"anyOf": [
266+
{
267+
"type": "string"
268+
},
269+
{
270+
"type": "array",
271+
"items": {
272+
"type": "string"
273+
}
274+
}
275+
],
276+
"description": "Labels your requests for the purpose of identification during usage reporting."
277+
},
278+
"extra": {
279+
"anyOf": [
280+
{
281+
"type": "string"
282+
},
283+
{
284+
"type": "array",
285+
"items": {
286+
"type": "string"
287+
}
288+
}
289+
],
290+
"description": "Arbitrary key-value pairs that are attached to the API response for usage in downstream processing."
291+
},
292+
"mip_opt_out": {
293+
"type": "boolean",
294+
"nullable": true,
295+
"description": "Opt out of the Deepgram Model Improvement Program for this request."
296+
},
297+
"version": {
298+
"type": "string",
299+
"description": "Model version to use (e.g. \"latest\" or a specific version string). Defaults to latest."
300+
}
301+
},
302+
"required": [
303+
"model"
304+
],
305+
"title": "nova-3-medical"
306+
}
307+
}
308+
}
309+
},
310+
"responses": {
311+
"200": {
312+
"content": {
313+
"application/json": {
314+
"schema": {
315+
"type": "object",
316+
"properties": {
317+
"generation_id": {
318+
"type": "string",
319+
"description": "The unique identifier of the created transcription task. Use this ID to retrieve the result via GET /v1/stt/{generation_id}.",
320+
"example": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
321+
}
322+
},
323+
"required": [
324+
"generation_id"
325+
]
326+
}
327+
}
328+
}
329+
}
330+
},
331+
"x-hideTryItPanel": true,
332+
"x-codeSamples": [
333+
{
334+
"lang": "cURL",
335+
"source": "curl -L \\\n --request POST \\\n --url 'https://api.aimlapi.com/v1/stt/create' \\\n --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \\\n --header 'Content-Type: application/json' \\\n --data '{\n \"model\": \"nova-3-medical\",\n \"url\": \"https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3\"\n }'"
336+
},
337+
{
338+
"lang": "JavaScript",
339+
"source": "async function main() {\n const response = await fetch('https://api.aimlapi.com/v1/stt/create', {\n method: 'POST',\n headers: {\n 'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',\n 'Content-Type': 'application/json',\n },\n body: JSON.stringify({\n \"model\": \"nova-3-medical\",\n \"url\": \"https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3\"\n }),\n });\n\n const data = await response.json();\n console.log(JSON.stringify(data, null, 2));\n}\n\nmain();"
340+
},
341+
{
342+
"lang": "Python",
343+
"source": "import requests\nimport json\n\nresponse = requests.post(\n \"https://api.aimlapi.com/v1/stt/create\",\n headers={\n \"Content-Type\": \"application/json\",\n \"Authorization\": \"Bearer <YOUR_AIMLAPI_KEY>\",\n },\n json={\n \"model\": \"nova-3-medical\",\n \"url\": \"https://audio-samples.github.io/samples/mp3/blizzard_primed/sample-0.mp3\"\n }\n)\n\ndata = response.json()\nprint(json.dumps(data, indent=2, ensure_ascii=False))"
344+
}
345+
]
346+
}
347+
}
348+
},
349+
"components": {
350+
"securitySchemes": {
351+
"access-token": {
352+
"scheme": "bearer",
353+
"bearerFormat": "<YOUR_AIMLAPI_KEY>",
354+
"type": "http",
355+
"description": "Bearer key"
356+
}
357+
}
358+
}
359+
}

0 commit comments

Comments
 (0)