> ## Documentation Index > Fetch the complete documentation index at: https://aisa.one/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > - Base URLs: models `https://api.aisa.one/v1` (Gemini GenerateContent: `https://api.aisa.one/v1beta`); data APIs `https://api.aisa.one/apis/v1`. The `servers` of each operation in https://aisa.one/openapi.yaml is authoritative. > - Auth: `Authorization: Bearer $AISA_API_KEY`. Never print, log, or commit the key. > - MCP (preferred for agents): `https://mcp.aisa.one/mcp`, signed in with OAuth, so there is no key to paste. > - Agent Skill: `npx skills add AIsa-team/agent-skills --skill aisa`. Fallback with the AIsa CLI: `aisa skills install aisa`. > - Spending: docs, https://aisa.one/models, https://aisa.one/api, `/v1/models`, and MCP `search`, `list_categories`, `get_details`, `batch_quote`, and the `account` operation are free. Quote the exact calls before running them (MCP `batch_quote`, CLI `aisa quote --json`). If the quote reports `auto_execute_eligible: true`, run it unless the user set a tighter limit or asked only for a quote. Otherwise, tell the user in one message the planned calls, the quoted price, and a total USD budget for the task, then wait for approval. Direct HTTP calls follow the stricter rule at https://aisa.one/docs/get-started/cli.md#direct-http-fallback. Do not make paid calls to test availability. Full rule: https://aisa.one/llms.txt # Transcribe Pre-recorded Audio > 按用量计费；默认请求预估费用：$0.0103 USD（不是固定价格）。 声明的单位费率：每 provider_credit $0.000001 USD。 最终费用以账户适用价格及实际结算为准。 ## 请求规范 * **方法与路径:** POST /apis/v1/deepgram/speech-to-text-pre-recorded * **可用状态:** enabled * **请求 URL 模板:** `https://api.aisa.one/apis/v1/deepgram/speech-to-text-pre-recorded` * **Runtime 事实版本:** 28061d27008061cbecfcaf7d1a3f1cc9280a40fce8644055c6968a360c2daf23 [完整 OpenAPI 定义](https://aisa.one/docs/reference-contracts/zh/deepgram.json) 有效请求与价格声明（包括认证和引用的 schema）： ```json theme={null} { "operationId": "deepgram.speech-to-text-pre-recorded", "method": "POST", "path": "/apis/v1/deepgram/speech-to-text-pre-recorded", "servers": [ { "url": "https://api.aisa.one" } ], "parameters": [], "security": [ { "bearerAuth": [] } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "audio_url", "content_type" ], "properties": { "tier": { "type": "string", "const": "enhanced", "description": "Enhanced tier for higher-accuracy recognition. Requires your own Deepgram key." }, "model": { "type": "string", "examples": [ "nova-3" ], "description": "Deepgram model to use (e.g., 'nova-3', 'general', 'phonecall'). Without your own Deepgram key, only 'nova-3' is supported and is used when omitted." }, "diarize": { "type": "boolean", "description": "Enable speaker diarization if true. Requires your own Deepgram key." }, "keyterm": { "type": "array", "items": { "type": "string" }, "examples": [ [ "invoice", "payment terms", "customer name" ] ], "description": "List of keyterms to boost in the transcript. Supported by Nova-3 and Flux models only. Use simple terms without intensifiers (e.g., 'invoice', 'payment terms'). For other models, use 'keywords' instead. Requires your own Deepgram key." }, "version": { "type": "string", "description": "Specific model version to use. Requires your own Deepgram key." }, "keywords": { "type": "array", "items": { "type": "string" }, "examples": [ [ "invoice:5", "payment:3" ] ], "description": "List of keywords to boost in the transcript. Supported by Nova-2, Nova-1, Enhanced, and Base models. Format: 'keyword:intensifier' (e.g., 'invoice:5'). For Nova-3 or Flux models, use 'keyterm' instead. Requires your own Deepgram key." }, "language": { "type": "string", "examples": [ "en-US" ], "description": "Language code for transcription (e.g., 'en-US'). Without your own Deepgram key, only 'en' or 'en-US' is supported and 'en' is used when omitted." }, "audio_url": { "type": "string", "format": "uri", "examples": [ "https://example.com/audio.wav" ], "maxLength": 2083, "minLength": 1, "description": "Public URL of the audio file to transcribe. Must be a direct, publicly downloadable media file URL — not a preview page, auth-gated link, or expiring/short-lived URL." }, "punctuate": { "type": "boolean", "description": "Automatically punctuate transcript." }, "alternatives": { "type": "integer", "minimum": 1, "description": "Number of alternative transcripts to return." }, "content_type": { "enum": [ "audio/wav", "audio/mp3", "audio/mpeg", "audio/flac", "audio/webm" ], "type": "string", "examples": [ "audio/wav", "audio/mp3" ], "description": "MIME type of the audio file. Without your own Deepgram key, only 'audio/wav' is supported." }, "smart_format": { "type": "boolean", "description": "Apply smart formatting (capitalization/punctuation)." }, "detect_language": { "type": "boolean", "description": "Automatically detect language if true. Prefer explicit `language` over this when the audio language is known; auto-detection reduces accuracy for non-English content. Requires your own Deepgram key." }, "interim_results": { "type": "boolean", "description": "Return interim results if true. Requires your own Deepgram key." } } } } } }, "x-aisa-status": "enabled", "x-aisa-pricing": { "cost_contract": "response_units", "customer_multiplier": 1.0, "customer_pricing": "provider_cost_multiplier", "default_request_estimate_usd": 0.0103, "estimate_source": "profile_seed", "evidence_source": "response_body", "maximum_units": 10000000, "unit": "provider_credit", "unit_rate_usd": 1e-06 }, "components": { "securitySchemes": { "bearerAuth": { "scheme": "bearer", "type": "http" } } } } ``` ## 费用与请求规则 按用量计费；默认请求预估费用：\$0.0103 USD（不是固定价格）。 声明的单位费率：每 provider\_credit \$0.000001 USD。 最终费用以账户适用价格及实际结算为准。 公开参考值不是你的账户报价或最终扣费。对于支持 X-AISA-Cost-Mode: quote 的接口，执行前请针对完整请求获取免费报价；执行后通过响应费用元数据和 Usage Logs 核对结算费用。1 USD 等于 1,000,000 个整数 micro-USD。 * **默认请求参考估价（USD）:** 0.0103 * **声明的单位费率（USD）:** 1e-06 * **计费单位:** provider\_credit * **计费依据:** response\_units * **公开参考倍率:** 1.0 * **声明的最大计数或单位数:** 10000000 * **结算证据来源:** response\_body ## OpenAPI ````yaml reference-contracts/zh/deepgram.json POST /apis/v1/deepgram/speech-to-text-pre-recorded openapi: 3.1.0 info: description: '' title: Deepgram version: '1' x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote x-aisa-configured-paths: - /apis/v1/deepgram/speech-to-text-pre-recorded x-aisa-document: facts_hash: 28061d27008061cbecfcaf7d1a3f1cc9280a40fce8644055c6968a360c2daf23 generator_version: '3' protocol_version: '1' schema_version: '1' composer_version: '28' response_pending: [] document_hash: sha256:d7961c913d511062935b50133b8836f9ae6092b6961f261b65b9237860c43b21 x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-provider: deepgram x-aisa-catalogs: deepgram: title: Deepgram description: '' x-aisa-document: facts_hash: 28061d27008061cbecfcaf7d1a3f1cc9280a40fce8644055c6968a360c2daf23 generator_version: '3' protocol_version: '1' schema_version: '1' x-aisa-plans: builder: 1 display_plan: payg payg: 1 similarweb_payg: 1 team: 1 version: e70a0959cd1b93b84ae16dffd7a538273ddb9c1d46277b82823c37ff1b6bc0fb x-aisa-capabilities: idempotency: Idempotency-Key max_price: X-AISA-Max-Price-USD quote: header: X-AISA-Cost-Mode value: quote servers: - url: https://api.aisa.one security: - bearerAuth: [] paths: /apis/v1/deepgram/speech-to-text-pre-recorded: post: tags: - Deepgram summary: Transcribe Pre-recorded Audio description: >- 按用量计费；默认请求预估费用：$0.0103 USD（不是固定价格）。 声明的单位费率：每 provider_credit $0.000001 USD。 最终费用以账户适用价格及实际结算为准。 operationId: deepgram.speech-to-text-pre-recorded requestBody: required: true content: application/json: schema: type: object required: - audio_url - content_type properties: tier: type: string const: enhanced description: >- Enhanced tier for higher-accuracy recognition. Requires your own Deepgram key. model: type: string examples: - nova-3 description: >- Deepgram model to use (e.g., 'nova-3', 'general', 'phonecall'). Without your own Deepgram key, only 'nova-3' is supported and is used when omitted. diarize: type: boolean description: >- Enable speaker diarization if true. Requires your own Deepgram key. keyterm: type: array items: type: string examples: - - invoice - payment terms - customer name description: >- List of keyterms to boost in the transcript. Supported by Nova-3 and Flux models only. Use simple terms without intensifiers (e.g., 'invoice', 'payment terms'). For other models, use 'keywords' instead. Requires your own Deepgram key. version: type: string description: >- Specific model version to use. Requires your own Deepgram key. keywords: type: array items: type: string examples: - - invoice:5 - payment:3 description: >- List of keywords to boost in the transcript. Supported by Nova-2, Nova-1, Enhanced, and Base models. Format: 'keyword:intensifier' (e.g., 'invoice:5'). For Nova-3 or Flux models, use 'keyterm' instead. Requires your own Deepgram key. language: type: string examples: - en-US description: >- Language code for transcription (e.g., 'en-US'). Without your own Deepgram key, only 'en' or 'en-US' is supported and 'en' is used when omitted. audio_url: type: string format: uri examples: - https://example.com/audio.wav maxLength: 2083 minLength: 1 description: >- Public URL of the audio file to transcribe. Must be a direct, publicly downloadable media file URL — not a preview page, auth-gated link, or expiring/short-lived URL. punctuate: type: boolean description: Automatically punctuate transcript. alternatives: type: integer minimum: 1 description: Number of alternative transcripts to return. content_type: enum: - audio/wav - audio/mp3 - audio/mpeg - audio/flac - audio/webm type: string examples: - audio/wav - audio/mp3 description: >- MIME type of the audio file. Without your own Deepgram key, only 'audio/wav' is supported. smart_format: type: boolean description: Apply smart formatting (capitalization/punctuation). detect_language: type: boolean description: >- Automatically detect language if true. Prefer explicit `language` over this when the audio language is known; auto-detection reduces accuracy for non-English content. Requires your own Deepgram key. interim_results: type: boolean description: >- Return interim results if true. Requires your own Deepgram key. responses: '200': description: Tool result data content: application/json: schema: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__public_data default: content: application/json: schema: {} description: >- Error response; upstream passthrough responses may use provider formats components: schemas: Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__public_data: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__f787f28144cb1000 Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__f787f28144cb1000: type: object required: - metadata - results properties: results: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__90f4cc22b0446387 metadata: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__b11703a09b349243 warnings: type: array items: type: string Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__90f4cc22b0446387: type: object required: - channels properties: channels: type: array items: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__a6f230b99dd63cc3 utterances: type: array items: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__329f847bda6fb35c Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__b11703a09b349243: type: object required: - request_id - channels - duration - created properties: models: type: array items: type: string sha256: type: string created: type: string channels: type: integer duration: type: number model_info: type: object additionalProperties: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__2a1112e0e7642695 request_id: type: string transaction_key: type: string Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__a6f230b99dd63cc3: type: object required: - alternatives properties: alternatives: type: array items: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__b95643d0ce65e905 Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__329f847bda6fb35c: type: object required: - transcript - confidence - speaker - start - end properties: end: type: number start: type: number speaker: type: integer confidence: type: number transcript: type: string Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__2a1112e0e7642695: type: object required: - name - version - arch properties: arch: type: string name: type: string version: type: string Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__b95643d0ce65e905: type: object required: - transcript - confidence - words properties: words: type: array items: $ref: >- #/components/schemas/Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__c69a99a7b146fc96 confidence: type: number transcript: type: string Response576A0Ea506F3_connect_DEEPGRAM_SPEECH_TO_TEXT_PRE_RECORDED__output__c69a99a7b146fc96: type: object required: - word - start - end - confidence properties: end: type: number word: type: string start: type: number speaker: type: integer confidence: type: number punctuated_word: type: string speaker_confidence: type: number securitySchemes: bearerAuth: scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.