> ## Documentation Index > Fetch the complete documentation index at: https://assemblyai.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create speech (OpenAI compatible) > The request shape of the OpenAI speech API (`POST /v1/audio/speech`), so an OpenAI SDK, or a framework built on one, works with the base URL `https://tts.us.assemblyai.com/v1/openai` (or the EU host) and your AssemblyAI API key as its API key. It shares its behaviour with [Create speech](/tts/api-reference/http-api/create-speech): the status waits for the first audio, the audio streams as it is synthesized, a failure after that point cuts the connection, and the same limits and billing apply. **Fields.** `model` and `input` are required. `model` takes a language's model name such as `assemblyai-tts-en`, or a model's name such as `assemblyai-tts-1` (the `assemblyai/` prefix is accepted); a name that is not an AssemblyAI model name, OpenAI's model names such as `tts-1` included, is refused with `400`, code `model_not_found`, and so is a model name the region does not serve. `voice` takes the library slug of an AssemblyAI voice, such as `aai-jane`, a voice's UUID, or an OpenAI voice name, each mapped to an AssemblyAI voice: `alloy` to `aai-jane`, `ash` to `aai-michael`, `ballad` to `aai-charles`, `cedar` to `aai-george`, `coral` to `aai-anna`, `echo` to `aai-paul`, `fable` to `aai-charles`, `marin` to `aai-mary`, `nova` to `aai-eve`, `onyx` to `aai-george`, `sage` to `aai-vera`, `shimmer` to `aai-alba` and `verse` to `aai-michael`; in a language other than English, an OpenAI voice name speaks with the language's default voice, `aai-jane`. A bare AssemblyAI voice name such as `jane` is refused with `422` on `voice`, and the message names its slug. A [cloned voice](/tts/openai-compatibility#cloned-voices) goes in `voice` as `{"id": ""}` or as a string holding its UUID. `response_format` is `mp3` (default, 24 kHz at 64 kbps), `pcm`, `wav`, `mulaw` or `alaw`; `opus`, `aac` and `flac` are refused. `stream_format: "sse"` streams the audio as OpenAI speech events instead of raw bytes. Fields this route does not use, such as `instructions` and `user`, are ignored and listed in `X-TTS-Unknown-Params`. **Extensions.** `language` (a language name such as `english`, or an ISO 639-1 code such as `en`), `sample_rate`, `voice_id` (a cloned voice's ID or slug, with `voice` left out) and `extend_biometric_consent` (renews a cloned voice's consent; see [Renew consent](/tts/cloned-voices#renew-consent)) may be added to the body; most OpenAI clients pass them through an extra-body option. A `language` that contradicts `model` is refused. The language is the one you set, else the one the model name implies (`assemblyai-tts-es` asks for Spanish), else a cloned voice's own language, else English. A request in a language no model of the region speaks is refused with `400`, code `invalid_request`; see [Languages](/tts/voices#languages). **SSE.** With `stream_format: "sse"` the body is `text/event-stream` of `data:` lines only: `{"type":"speech.audio.delta","audio":""}` for each piece of audio, the next bytes of the requested format, then one `{"type":"speech.audio.done","usage":{...}}`. There is no `[DONE]` line. While nothing is sent for 15 seconds, a comment line `: keepalive` arrives; ignore lines that start with `:`. A failure after the first audio sends `{"type":"error","error":{...}}` and then cuts the connection. **Errors** use the OpenAI body (`OpenAIErrorResponse`), with the same `code` the native routes use and an OpenAI `type`. Text with nothing to speak is refused with `400`, code `invalid_request` (`input produced no speech`), and is not billed. ## OpenAPI ````yaml api-reference/specs/streaming-tts-speech.yaml POST /v1/openai/audio/speech openapi: 3.0.3 info: title: AssemblyAI Streaming TTS HTTP API description: >- HTTP API of Streaming Text-to-Speech: send a text in one `POST` and read the speech back as the response body. The audio streams while it is synthesized, so the first bytes arrive long before the last; with `"stream": false` the whole clip arrives at once. `POST /v1/speech/events` streams the audio as server-sent events with word timings, and `POST /v1/openai/audio/speech` takes the request shape of the OpenAI speech API, so OpenAI SDKs and the frameworks built on them work by changing their base URL. See the [Quickstart](/tts/getting-started/quickstart) for a first request and [OpenAI compatibility](/tts/openai-compatibility) for the OpenAI-compatible route. Voices, models, audio formats and text handling are those of the [Streaming TTS WebSocket API](/tts/connect-parameters). Every error the native routes answer has the JSON body described under `ErrorResponse`, and every error of the OpenAI-compatible routes the body described under `OpenAIErrorResponse`; see [HTTP API basics](/tts/api-reference/http-api/overview). version: 1.0.0 termsOfService: https://www.assemblyai.com/legal/terms-of-service contact: name: API Support email: support@assemblyai.com url: https://www.assemblyai.com/docs/ servers: - url: https://tts.us.assemblyai.com description: US data zone x-fern-server-name: US - url: https://tts.eu.assemblyai.com description: EU data zone x-fern-server-name: EU security: - apiKey: [] tags: - name: Speech description: Text to speech in one request. - name: OpenAI compatibility description: The route and the models documents for OpenAI-shaped clients. paths: /v1/openai/audio/speech: post: tags: - OpenAI compatibility summary: Create speech (OpenAI compatible) description: >- The request shape of the OpenAI speech API (`POST /v1/audio/speech`), so an OpenAI SDK, or a framework built on one, works with the base URL `https://tts.us.assemblyai.com/v1/openai` (or the EU host) and your AssemblyAI API key as its API key. It shares its behaviour with [Create speech](/tts/api-reference/http-api/create-speech): the status waits for the first audio, the audio streams as it is synthesized, a failure after that point cuts the connection, and the same limits and billing apply. **Fields.** `model` and `input` are required. `model` takes a language's model name such as `assemblyai-tts-en`, or a model's name such as `assemblyai-tts-1` (the `assemblyai/` prefix is accepted); a name that is not an AssemblyAI model name, OpenAI's model names such as `tts-1` included, is refused with `400`, code `model_not_found`, and so is a model name the region does not serve. `voice` takes the library slug of an AssemblyAI voice, such as `aai-jane`, a voice's UUID, or an OpenAI voice name, each mapped to an AssemblyAI voice: `alloy` to `aai-jane`, `ash` to `aai-michael`, `ballad` to `aai-charles`, `cedar` to `aai-george`, `coral` to `aai-anna`, `echo` to `aai-paul`, `fable` to `aai-charles`, `marin` to `aai-mary`, `nova` to `aai-eve`, `onyx` to `aai-george`, `sage` to `aai-vera`, `shimmer` to `aai-alba` and `verse` to `aai-michael`; in a language other than English, an OpenAI voice name speaks with the language's default voice, `aai-jane`. A bare AssemblyAI voice name such as `jane` is refused with `422` on `voice`, and the message names its slug. A [cloned voice](/tts/openai-compatibility#cloned-voices) goes in `voice` as `{"id": ""}` or as a string holding its UUID. `response_format` is `mp3` (default, 24 kHz at 64 kbps), `pcm`, `wav`, `mulaw` or `alaw`; `opus`, `aac` and `flac` are refused. `stream_format: "sse"` streams the audio as OpenAI speech events instead of raw bytes. Fields this route does not use, such as `instructions` and `user`, are ignored and listed in `X-TTS-Unknown-Params`. **Extensions.** `language` (a language name such as `english`, or an ISO 639-1 code such as `en`), `sample_rate`, `voice_id` (a cloned voice's ID or slug, with `voice` left out) and `extend_biometric_consent` (renews a cloned voice's consent; see [Renew consent](/tts/cloned-voices#renew-consent)) may be added to the body; most OpenAI clients pass them through an extra-body option. A `language` that contradicts `model` is refused. The language is the one you set, else the one the model name implies (`assemblyai-tts-es` asks for Spanish), else a cloned voice's own language, else English. A request in a language no model of the region speaks is refused with `400`, code `invalid_request`; see [Languages](/tts/voices#languages). **SSE.** With `stream_format: "sse"` the body is `text/event-stream` of `data:` lines only: `{"type":"speech.audio.delta","audio":""}` for each piece of audio, the next bytes of the requested format, then one `{"type":"speech.audio.done","usage":{...}}`. There is no `[DONE]` line. While nothing is sent for 15 seconds, a comment line `: keepalive` arrives; ignore lines that start with `:`. A failure after the first audio sends `{"type":"error","error":{...}}` and then cuts the connection. **Errors** use the OpenAI body (`OpenAIErrorResponse`), with the same `code` the native routes use and an OpenAI `type`. Text with nothing to speak is refused with `400`, code `invalid_request` (`input produced no speech`), and is not billed. operationId: CreateSpeechOpenAI parameters: - $ref: '#/components/parameters/ClientRequestIdStrict' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/OpenAISpeechRequest' examples: pcm: summary: Raw PCM for a voice agent value: model: assemblyai-tts-en input: Hi! Thanks for calling. voice: alloy response_format: pcm assemblyai_voice: summary: An AssemblyAI library voice by its ID value: model: assemblyai-tts-en input: Thanks for calling. voice: 49c443a4-8a1d-5f7e-b70b-98bdbd9823c3 cloned_voice: summary: A cloned voice by its ID value: model: assemblyai-tts-en input: Thanks for calling. voice: id: 01a139bf-78a0-7d18-9a4e-6c0f2b8d1e37 response_format: pcm sse: summary: Speech events value: model: assemblyai-tts-en input: Hello from AssemblyAI. response_format: pcm stream_format: sse responses: '200': description: The audio, or speech events with `stream_format` `sse`. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' X-Generation-Id: $ref: '#/components/headers/X-Generation-Id' X-Client-Request-Id: $ref: '#/components/headers/X-Client-Request-Id' X-TTS-Region: $ref: '#/components/headers/X-TTS-Region' X-TTS-Model: $ref: '#/components/headers/X-TTS-Model' X-TTS-Voice-Id: $ref: '#/components/headers/X-TTS-Voice-Id' X-TTS-Voice-Expires-At: $ref: '#/components/headers/X-TTS-Voice-Expires-At-OpenAI' X-TTS-Voice-Alias: $ref: '#/components/headers/X-TTS-Voice-Alias' X-TTS-Language: $ref: '#/components/headers/X-TTS-Language' X-TTS-Encoding: $ref: '#/components/headers/X-TTS-Encoding' X-TTS-Sample-Rate: $ref: '#/components/headers/X-TTS-Sample-Rate' X-TTS-Container: $ref: '#/components/headers/X-TTS-Container' X-TTS-Bit-Rate: $ref: '#/components/headers/X-TTS-Bit-Rate' X-TTS-Billed-Characters: $ref: '#/components/headers/X-TTS-Billed-Characters' X-TTS-Unknown-Params: $ref: '#/components/headers/X-TTS-Unknown-Params' Server-Timing: $ref: '#/components/headers/Server-Timing' X-Accel-Buffering: $ref: '#/components/headers/X-Accel-Buffering' Cache-Control: $ref: '#/components/headers/Cache-Control' content: audio/mpeg: schema: $ref: '#/components/schemas/AudioBody' audio/pcm: schema: $ref: '#/components/schemas/AudioBody' audio/wav: schema: $ref: '#/components/schemas/AudioBody' audio/PCMU: schema: $ref: '#/components/schemas/AudioBody' audio/PCMA: schema: $ref: '#/components/schemas/AudioBody' text/event-stream: schema: type: string description: >- Speech events, one `data:` line each: `SpeechAudioDeltaEvent` objects, then one `SpeechAudioDoneEvent`, or an `OpenAISseErrorEvent` before a cut. Comment lines (`: keepalive`) may arrive between them. example: >- data: {"type":"speech.audio.delta","audio":"AAAAAP7/AQD+/wIA"} data: {"type":"speech.audio.done","usage":{"input_tokens":0,"output_tokens":0,"total_tokens":0,"input_characters":22,"billed_characters":22,"audio_duration_seconds":1.62}} '400': $ref: '#/components/responses/OpenAIBadRequest' '401': $ref: '#/components/responses/OpenAIUnauthorized' '402': $ref: '#/components/responses/OpenAIPaymentRequired' '403': $ref: '#/components/responses/OpenAIForbidden' '404': $ref: '#/components/responses/OpenAINotFound' '405': $ref: '#/components/responses/OpenAIMethodNotAllowed' '408': $ref: '#/components/responses/OpenAIRequestTimeout' '413': $ref: '#/components/responses/OpenAITooLarge' '422': $ref: '#/components/responses/OpenAIUnprocessable' '429': $ref: '#/components/responses/OpenAIRateLimited' '500': $ref: '#/components/responses/OpenAIInternalError' '503': $ref: '#/components/responses/OpenAIUnavailable' components: parameters: ClientRequestIdStrict: name: X-Client-Request-Id in: header required: false schema: type: string minLength: 1 maxLength: 512 description: >- Your own id for the request, 1 to 512 printable ASCII characters, echoed in the response. An invalid value is refused with `400`, code `invalid_parameter`. schemas: OpenAISpeechRequest: type: object required: - model - input description: >- The OpenAI speech request. Fields this route does not use are ignored and listed in `X-TTS-Unknown-Params`. properties: model: type: string description: >- A language's model name, such as `assemblyai-tts-en` (the language follows the code), or a model's name such as `assemblyai-tts-1`, optionally prefixed `assemblyai/`. Case-insensitive. A name that is not an AssemblyAI model name, OpenAI's model names such as `tts-1` included, is refused with `model_not_found`, and so is a model name the region does not serve. input: type: string minLength: 1 maxLength: 5000 description: >- The text to speak, 1 to 5,000 Unicode code points, not blank. An array is refused. voice: oneOf: - type: string - type: object required: - id properties: id: type: string minLength: 1 maxLength: 64 description: The ID or slug of a cloned voice. description: >- The library slug of an AssemblyAI voice, such as `aai-jane`, a voice's UUID, or an OpenAI voice name mapped to an AssemblyAI voice: `alloy` (`aai-jane`), `ash` (`aai-michael`), `ballad` (`aai-charles`), `cedar` (`aai-george`), `coral` (`aai-anna`), `echo` (`aai-paul`), `fable` (`aai-charles`), `marin` (`aai-mary`), `nova` (`aai-eve`), `onyx` (`aai-george`), `sage` (`aai-vera`), `shimmer` (`aai-alba`) or `verse` (`aai-michael`), in English; in a language other than English, an OpenAI voice name speaks with the language's default voice, `aai-jane`. OpenAI voice names are case-insensitive; a slug is lowercase. A bare AssemblyAI voice name such as `jane` is refused with `422` (`invalid_parameter`) and `param` `voice`, and the message names its slug. Other values are not supported: a misspelt name, a file name, a path or a URL is refused with `422` like a bare name, and a slug or UUID that names no voice with `400` (`invalid_request`) or, where cloned voices are not available, `403`. Left out, the default voice of the model and language, `aai-jane`. A [cloned voice](/tts/openai-compatibility#cloned-voices) goes in as `{"id": ""}`, or as a string holding its UUID; the slug of one of your voices in a plain string is refused. response_format: type: string enum: - mp3 - pcm - wav - mulaw - alaw default: mp3 description: >- `mp3` (24 kHz, 64 kbps), `pcm` (raw 16-bit little-endian), `wav` (16-bit PCM in a WAV file), `mulaw` or `alaw` (raw G.711), case-insensitive. The sample rate is 24 kHz unless `sample_rate` says otherwise. `opus`, `aac` and `flac` are refused. stream_format: type: string enum: - audio - sse default: audio description: >- `audio` streams the audio bytes; `sse` streams speech events. Case-insensitive. speed: type: number description: Accepted when it equals `1`; any other value is refused. language: type: string description: >- Extension: the language to speak, as a name (`english`) or an ISO 639-1 code (`en`). Refused when it differs from the language `model` implies. sample_rate: type: integer enum: - 8000 - 16000 - 22050 - 24000 - 44100 - 48000 default: 24000 description: 'Extension: the sample rate of the audio in Hz.' voice_id: type: string minLength: 1 maxLength: 64 description: >- Extension: the ID or slug of a cloned voice, for clients that cannot send `voice` as an object. Leave `voice` out; next to any other `voice`, such as `alloy` or `aai-jane`, it is refused with `invalid_parameter`. extend_biometric_consent: type: boolean default: false description: >- Extension: `true` renews the biometric consent of a cloned voice, and attests renewed consent on behalf of the account that owns the voice; see [Renew consent](/tts/cloned-voices#renew-consent). Only the voice's owner may set it. The voice must be named as `{"id": ...}` in `voice`, as its UUID in the `voice` string, or in `voice_id`: with no voice, or a slug such as `aai-jane` in the `voice` string, it is refused with `invalid_parameter` (`extend_biometric_consent: needs the voice by its id: {"id": ...} or a voice id in voice`), and on another account's voice, or with an OpenAI voice name such as `alloy` in an English request, with `not_owner`. In another language, an OpenAI voice name is refused with `invalid_parameter`. The renewal is not guaranteed: one that cannot be made leaves the expiry as it was. word_boundaries: type: boolean default: false description: >- Must be `false` or left out; word timings come from `POST /v1/speech/events`. example: model: assemblyai-tts-en input: Hi! Thanks for calling. voice: alloy response_format: pcm AudioBody: type: string format: binary description: >- Raw audio in the requested format. Streamed responses are chunked and end cleanly only when the audio is complete. OpenAIErrorResponse: type: object required: - error description: The body of every error of the OpenAI-compatible routes. properties: error: $ref: '#/components/schemas/OpenAIError' OpenAIError: type: object required: - message - type - code - request_id - retryable properties: message: type: string description: What went wrong, written for people. type: type: string description: >- The OpenAI error type: `invalid_request_error`, `authentication_error`, `permission_error`, `insufficient_quota`, `rate_limit_error`, `server_error` or `service_unavailable_error`. param: type: string nullable: true description: The field the error is about, or `null`. code: type: string description: The same code the native routes answer, such as `invalid_parameter`. request_id: type: string description: The request's id, also in the `X-Request-Id` header. retryable: type: boolean description: Whether the same request can succeed when you retry it later. retry_after_seconds: type: integer nullable: true description: Seconds to wait before retrying; `null` when there is no hint. headers: X-Request-Id: description: >- The request's id, a UUID, on every response, errors and the answer to a browser's CORS preflight included. It is the `id` of the `Begin` event and the `request_id` of an error body. Quote it in support requests. schema: type: string X-Generation-Id: description: The same value as `X-Request-Id`, for clients that read a generation id. schema: type: string X-Client-Request-Id: description: The `X-Client-Request-Id` the request sent, when it was valid. schema: type: string X-TTS-Region: description: The region that served the request, such as `us-east-1`. schema: type: string X-TTS-Model: description: >- The name of the model that spoke, such as `assemblyai-tts-1`, on every `200`. It is the model the request named, else the default model of the request's language, and the same value as `model` in the `Begin` event of `/v1/speech/events`. schema: type: string X-TTS-Voice-Id: description: >- The voice the request spoke, as `voice_id` names it and as `Begin.configuration.voice_id` reports it on `/v1/speech/events`, on every `200`. It is the `voice_id` the request sent, trimmed, with a UUID in lowercase, or the default voice's library slug, such as `aai-jane`, when the request named no voice. schema: type: string X-TTS-Voice-Expires-At-OpenAI: description: >- When the consent period of the request's cloned voice ends, as a Unix timestamp in seconds, as the request started. Present on a `200` that spoke a cloned voice of your account with a consent period; see [Voice cloning](/tts/cloned-voices#consent-period). The route always streams, so the headers leave with the first audio, before a renewal with `extend_biometric_consent` can move the expiry. schema: type: integer X-TTS-Voice-Alias: description: >- The OpenAI voice name the request used, such as `alloy`, when it used one. schema: type: string X-TTS-Language: description: The language spoken, such as `english`. schema: type: string X-TTS-Encoding: description: >- The encoding of the audio, in canonical form (`mulaw` is reported as `pcm_mulaw`). schema: type: string X-TTS-Sample-Rate: description: The sample rate of the audio in Hz. schema: type: integer X-TTS-Container: description: '`raw` or `wav`. Absent on MP3.' schema: type: string X-TTS-Bit-Rate: description: The MP3 bit rate in bits per second. Present on MP3 only. schema: type: integer X-TTS-Billed-Characters: description: >- The characters the request bills once its body is delivered, in Unicode code points of the text as sent; `0` for text with nothing to speak. A streamed response sends it with the first audio, before the outcome is known; a failure on our side that then cuts the body, or ends it with an `Error` event, makes the request free. The final count is `Termination.billed_characters` on `/v1/speech/events` and `usage.billed_characters` of `speech.audio.done`. schema: type: integer X-TTS-Unknown-Params: description: >- The names of the body fields the route ignored, sorted and comma-separated, at most 16. Present when the body had any. schema: type: string Server-Timing: description: >- `open;dur=, model;dur=, ttfa;dur=`: `open` from receipt to the start of synthesis (authentication, validation and the voice lookup), `model` from the start of synthesis to the first audio, `ttfa` from receipt to the first audio byte sent. Browsers show it in their network panel. schema: type: string X-Accel-Buffering: description: >- `no`, on streamed responses, so that proxies pass the audio on as it arrives. schema: type: string Cache-Control: description: >- `no-store, no-transform`: the audio is never cached or recompressed on the way. schema: type: string WWW-Authenticate: description: '`Bearer realm="assemblyai"`. On every `401`.' schema: type: string Allow: description: The methods the path answers, such as `OPTIONS, POST`. schema: type: string Retry-After: description: >- Whole seconds to wait before retrying. On every `429` and `503` with an error body. schema: type: integer responses: OpenAIBadRequest: description: >- Type `invalid_request_error`. Every refusal that the native routes answer with `400` or `422`, except `feature_not_enabled` (`403` here), answers `400` here with the same `code`, such as `invalid_message`, `invalid_parameter` and `invalid_request`; also `model_not_found` for a `model` that is not an AssemblyAI model name, `invalid_request` for text with nothing to speak (`input produced no speech`), and `invalid_parameter` for an invalid `X-Client-Request-Id`. A cloned voice that cannot be used answers `voice_not_found`, `voice_expired`, `voice_blocked`, `voice_not_paired` or `model_retired`, and `extend_biometric_consent` on a voice that another account owns answers `not_owner`; a voice UUID in the `voice` string that is not found is answered like an unknown voice name, `invalid_request`. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' examples: model_not_found: summary: A model that is not an AssemblyAI model value: error: message: >- model: 'tts-1' is not an AssemblyAI model; use one of GET /v1/openai/models, such as assemblyai-tts-en type: invalid_request_error param: model code: model_not_found request_id: 93309b7e-9131-474f-99e4-6e0623463374 retryable: false retry_after_seconds: null voice_not_paired: summary: A cloned voice not paired with the request's model value: error: message: >- Voice 01a139bf-78a0-7d18-9a4e-6c0f2b8d1e37 has no ready pairing with model assemblyai-tts-1. Name a model the voice is paired with, or pair the voice with this model, wait until the pairing is ready, and try again. type: invalid_request_error param: model code: voice_not_paired request_id: 4b8d2f61-9c3a-4e7b-b5d0-2a6f8c1e9d34 retryable: false retry_after_seconds: null OpenAIUnauthorized: description: >- Type `authentication_error`, code `missing_authorization` or `unauthorized`. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' WWW-Authenticate: $ref: '#/components/headers/WWW-Authenticate' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIPaymentRequired: description: >- Type `insufficient_quota`, code `insufficient_funds`: the account has no funds for the request. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIForbidden: description: >- Type `permission_error`, code `feature_not_enabled`: cloned voices are not available on this host, for a voice sent as `{"id": ...}` or in `voice_id`. Where cloned voices are not available, a voice UUID in the `voice` string is answered like an unknown voice name (`400`), and a model's name such as `assemblyai-tts-1` in `model`, sent without a cloned voice, with `400` `model_not_found`. Code `biometric_terms_not_accepted`, also `permission_error`: the account has not accepted the biometric data terms a cloned voice needs. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAINotFound: description: >- Type `invalid_request_error`, code `not_found`: a path the API does not serve, an unknown path or a documented one with a trailing slash. Paths are exact; nothing redirects. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIMethodNotAllowed: description: >- Type `invalid_request_error`, code `method_not_allowed`: a method the path does not answer; `Allow` lists the ones it does. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' Allow: $ref: '#/components/headers/Allow' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIRequestTimeout: description: >- Type `invalid_request_error`, code `request_timeout`: the body did not arrive within 10 seconds. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAITooLarge: description: >- Type `invalid_request_error`, code `request_too_large`: the body is over 131,072 bytes. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIUnprocessable: description: >- Type `invalid_request_error`, code `invalid_parameter`, `param` `voice`: a `voice` string that is not an OpenAI voice name, a voice slug or a voice ID, such as a bare AssemblyAI voice name like `jane`, a misspelt name, a file name, a path or a URL. The message names the slug to send for an AssemblyAI voice's name, and `errors` lists every other failing field too. Every other invalid field on this route is a `400`. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' examples: bare_voice_name: summary: A bare AssemblyAI voice name in voice value: error: message: >- voice: must be an OpenAI voice name such as alloy, the slug of an AssemblyAI voice such as aai-jane, a voice ID, or {"id": ...} with the slug of one of your voices: for jane, send aai-jane type: invalid_request_error param: voice code: invalid_parameter request_id: 2c7e5a90-4f1b-4d8e-a6c3-9b0d1e2f3a45 retryable: false retry_after_seconds: null OpenAIRateLimited: description: >- Type `rate_limit_error`: code `rate_limited` when the account's requests per minute are used up; `at_capacity` when there is no room for the request just now, an `mp3` request included while the server encodes as many MP3 responses as it takes. Retry after `Retry-After`. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' Retry-After: $ref: '#/components/headers/Retry-After' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIInternalError: description: Type `server_error`, code `internal_error`. Retry. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' OpenAIUnavailable: description: >- Type `service_unavailable_error`, code `auth_unavailable`, `voice_service_unavailable`, `upstream_unavailable`, `service_restart` or `service_unavailable`. Retry after `Retry-After`. headers: X-Request-Id: $ref: '#/components/headers/X-Request-Id' Retry-After: $ref: '#/components/headers/Retry-After' content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' securitySchemes: apiKey: type: apiKey in: header name: Authorization description: >- Your AssemblyAI API key, or a temporary token, in the `Authorization` header. The raw key works directly; a `Bearer ` prefix is also accepted, which is what OpenAI SDKs send. Send exactly one `Authorization` header. The HTTP routes read the credential from this header only. ````