{"openapi":"3.1.0","info":{"title":"Deepgram via Locus MPP","version":"1.0.0","description":"Industry-leading speech AI — transcribe audio with Nova-3, generate speech with Flux or Aura-2 TTS, and analyze text for sentiment, topics, intents, and summaries.","contact":{"email":"api@paywithlocus.com"},"x-guidance":"Use the documented POST operations for Deepgram. Send JSON matching each requestBody schema. Unpaid public x402 requests return an x402 v2 payment challenge; retry the same body with PAYMENT-SIGNATURE and the returned x-locus-request-id."},"x-agentcash-guidance":{"llmsTxtUrl":"https://beta.paywithlocus.com/mpp/deepgram.md"},"x-service-info":{"categories":["ai"],"docs":{"homepage":"https://deepgram.com","apiReference":"https://developers.deepgram.com/reference/deepgram-api-overview","llms":"https://beta.paywithlocus.com/mpp/deepgram.md"}},"paths":{"/deepgram/transcribe":{"post":{"operationId":"deepgram_transcribe","summary":"Transcribe Audio","description":"Transcribe a pre-recorded audio file from a public URL using Deepgram Nova-3 (default). Returns the full transcript with optional enrichments: punctuation, speaker diarization, smart formatting, paragraphs, sentiment, summary, topics, intents, and entity detection.","tags":["AI / Speech"],"security":[],"x-payment-info":{"intent":"charge","method":"tempo","amount":"53000","currency":"0x20c000000000000000000000b9537d11c60e8b50","description":"$0.05 + $0.003 fee"},"parameters":[{"name":"x-locus-request-id","in":"header","required":false,"description":"UUID returned by the initial 402. Echo it on the paid retry and later recovery attempts.","schema":{"type":"string","format":"uuid"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"url":{"type":"string","description":"Publicly accessible URL of the audio file to transcribe"},"model":{"type":"string","description":"STT model to use (default: nova-3). Options: nova-3, nova-2, enhanced, base"},"language":{"type":"string","description":"BCP-47 language code (default: en). E.g. es, fr, de, ja"},"smart_format":{"type":"boolean","description":"Apply smart formatting (numbers, dates, punctuation). Recommended."},"punctuate":{"type":"boolean","description":"Add punctuation and capitalization"},"diarize":{"type":"boolean","description":"Identify and label individual speakers"},"paragraphs":{"type":"boolean","description":"Split transcript into readable paragraphs"},"summarize":{"type":"boolean","description":"Generate a summary of the audio content"},"sentiment":{"type":"boolean","description":"Detect emotional sentiment throughout the audio"},"topics":{"type":"boolean","description":"Identify topics discussed in the audio"},"intents":{"type":"boolean","description":"Detect speaker intents throughout the audio"},"detect_entities":{"type":"boolean","description":"Extract named entities (people, places, organizations)"}},"required":["url"],"additionalProperties":true},"example":{"url":"https://example.com"}}}},"responses":{"200":{"description":"Successful response with PAYMENT-RESPONSE and durable request receipt"},"202":{"description":"The supplied request ID is already in progress"},"400":{"description":"Invalid request"},"402":{"description":"Payment Required"},"409":{"description":"Request ID conflict or terminal failed request"}}}},"/deepgram/speak":{"post":{"operationId":"deepgram_speak","summary":"Text to Speech","description":"Convert text to natural-sounding speech using Deepgram Aura-2 voices. Returns base64-encoded audio (MP3 by default). Choose from 46+ English voices and voices in Spanish, French, German, Dutch, Italian, and Japanese.","tags":["AI / Speech"],"security":[],"x-payment-info":{"intent":"charge","method":"tempo","amount":"23000","currency":"0x20c000000000000000000000b9537d11c60e8b50","description":"$0.02 + $0.003 fee"},"parameters":[{"name":"x-locus-request-id","in":"header","required":false,"description":"UUID returned by the initial 402. Echo it on the paid retry and later recovery attempts.","schema":{"type":"string","format":"uuid"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"text":{"type":"string","description":"Text to convert to speech. Max ~2000 chars recommended per call."},"model":{"type":"string","description":"TTS voice model (default: aura-2-thalia-en). Format: aura-2-{voice}-{lang}. E.g. aura-2-apollo-en, aura-2-thalia-en, aura-2-orion-en"},"encoding":{"type":"string","description":"Audio encoding (default: mp3). Options: mp3, linear16, flac, mulaw, alaw, opus, aac"},"container":{"type":"string","description":"Audio container format. Options: mp3, wav, ogg, none"},"sample_rate":{"type":"string","description":"Output sample rate in Hz (e.g. 24000, 16000, 8000)"}},"required":["text"],"additionalProperties":true},"example":{"text":"Hello from x402"}}}},"responses":{"200":{"description":"Successful response with PAYMENT-RESPONSE and durable request receipt"},"202":{"description":"The supplied request ID is already in progress"},"400":{"description":"Invalid request"},"402":{"description":"Payment Required"},"409":{"description":"Request ID conflict or terminal failed request"}}}},"/deepgram/speak-flux":{"post":{"operationId":"deepgram_speak_flux","summary":"Flux Text to Speech","description":"Synthesize a complete block of text with Deepgram Flux TTS using the stateless batch REST transport. Returns base64-encoded audio.","tags":["AI / Speech"],"security":[],"x-payment-info":{"intent":"charge","method":"tempo","amount":null,"currency":"0x20c000000000000000000000b9537d11c60e8b50","description":"~$0.045 per 1,000 characters + $0.003 fee"},"parameters":[{"name":"x-locus-request-id","in":"header","required":false,"description":"UUID returned by the initial 402. Echo it on the paid retry and later recovery attempts.","schema":{"type":"string","format":"uuid"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"text":{"type":"string","description":"Complete block of text to synthesize"},"model":{"type":"string","description":"Flux voice model in flux-{voice}-{language} format (e.g. flux-haley-en, flux-alexis-en, flux-kit-en)"},"encoding":{"type":"string","description":"Audio encoding: mp3 (default), opus, flac, aac, linear16, mulaw, or alaw"},"container":{"type":"string","description":"Output container where applicable (e.g. wav or ogg)"},"sample_rate":{"type":"number","description":"Output sample rate; supported values depend on encoding"},"bit_rate":{"type":"number","description":"Bit rate for supported compressed encodings"},"speed":{"type":"number","description":"Speech-rate multiplier from 0.85 to 1.15 in 0.05 increments"},"expressivity":{"type":"number","description":"Delivery register from -2 (calmer) to 2 (more animated)"}},"required":["text","model"],"additionalProperties":true},"example":{"text":"Hello from x402","model":"in"}}}},"responses":{"200":{"description":"Successful response with PAYMENT-RESPONSE and durable request receipt"},"202":{"description":"The supplied request ID is already in progress"},"400":{"description":"Invalid request"},"402":{"description":"Payment Required"},"409":{"description":"Request ID conflict or terminal failed request"}}}},"/deepgram/analyze":{"post":{"operationId":"deepgram_analyze","summary":"Analyze Text","description":"Run Deepgram text intelligence on any text — sentiment analysis, topic detection, intent recognition, and summarization. Enable features via query parameters.","tags":["AI / Speech"],"security":[],"x-payment-info":{"intent":"charge","method":"tempo","amount":"13000","currency":"0x20c000000000000000000000b9537d11c60e8b50","description":"$0.01 + $0.003 fee"},"parameters":[{"name":"x-locus-request-id","in":"header","required":false,"description":"UUID returned by the initial 402. Echo it on the paid retry and later recovery attempts.","schema":{"type":"string","format":"uuid"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"text":{"type":"string","description":"Text to analyze"},"sentiment":{"type":"boolean","description":"Detect positive/negative/neutral sentiment"},"summarize":{"type":"boolean","description":"Generate a concise summary"},"topics":{"type":"boolean","description":"Identify topics in the text"},"intents":{"type":"boolean","description":"Detect speaker/writer intents"},"language":{"type":"string","description":"BCP-47 language code (default: en)"}},"required":["text"],"additionalProperties":true},"example":{"text":"Hello from x402"}}}},"responses":{"200":{"description":"Successful response with PAYMENT-RESPONSE and durable request receipt"},"202":{"description":"The supplied request ID is already in progress"},"400":{"description":"Invalid request"},"402":{"description":"Payment Required"},"409":{"description":"Request ID conflict or terminal failed request"}}}},"/deepgram/list-models":{"post":{"operationId":"deepgram_list_models","summary":"List Models","description":"List all available Deepgram STT and TTS models with their capabilities, supported languages, and metadata.","tags":["AI / Speech"],"security":[],"x-payment-info":{"intent":"charge","method":"tempo","amount":"4000","currency":"0x20c000000000000000000000b9537d11c60e8b50","description":"$0.001 + $0.003 fee"},"parameters":[{"name":"x-locus-request-id","in":"header","required":false,"description":"UUID returned by the initial 402. Echo it on the paid retry and later recovery attempts.","schema":{"type":"string","format":"uuid"}}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{},"additionalProperties":true},"example":{}}}},"responses":{"200":{"description":"Successful response with PAYMENT-RESPONSE and durable request receipt"},"202":{"description":"The supplied request ID is already in progress"},"400":{"description":"Invalid request"},"402":{"description":"Payment Required"},"409":{"description":"Request ID conflict or terminal failed request"}}}}}}