> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmix.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Speech > Generates audio from the input text. Returns the audio file content, or a stream of audio events. ## OpenAPI ````yaml /openapi.json post /v1/audio/speech openapi: 3.1.0 info: title: AIHubMix Gateway API description: | Unified multi-protocol gateway. Exposes three native shapes side-by-side: - OpenAI (`/v1/chat/completions`, `/v1/responses`, ...) - Anthropic (`/v1/messages`) - Gemini (`/v1beta/models/{model}:generateContent`) Each vendor's native SDK connects directly. Gateway-only fields are marked with `x-source.authority: gateway`. contact: name: AIHubMix Team version: 2.1.1 x-upstream: vendorSpecs: packageVersion: 0.1.1 installedFrom: npm sources: openai/official: version: '2026-05-31' hash: >- sha256:a203971a0bc0cd3b903b9488e3ac40eaa161a274dfaf172c1da73eee029147a8 anthropic/official: version: '2026-05-31' hash: >- sha256:f9d488f9290d78a081bed62fa0c040476b5d009f3db92c06c8e279e69df73fc9 layers: - role: L0-base source: avs://openai/official protocol: openai authority: official - role: L0-base source: avs://anthropic/official protocol: anthropic authority: official - role: gateway-other source: gateway/anthropic-mappings.yml protocol: all authority: gateway - role: horizontal-auth source: gateway/auth.yml protocol: all authority: gateway - role: horizontal-errors source: gateway/errors.yml protocol: all authority: gateway - role: L3-gateway source: gateway/openai-gateway.yml protocol: openai authority: gateway - role: gateway-other source: gateway/openai-image-mappings.yml protocol: all authority: gateway - role: gateway-other source: gateway/openai-mappings.yml protocol: all authority: gateway - role: L2-passthrough source: gateway/openai-passthrough.yml protocol: openai authority: gateway servers: - url: https://aihubmix.com description: Production - url: https://api.inferera.com description: Backup (use when the primary domain is unreachable) security: - gatewayBearer: [] tags: - name: OpenAI Compatible description: >- OpenAI-compatible endpoints (chat, completions, embeddings, images, audio, videos, moderations). - name: Anthropic Compatible description: Anthropic-native endpoints (messages with Anthropic protocol). - name: Google Vertex AI Compatible description: Google Gemini / Vertex AI endpoints. paths: /v1/audio/speech: post: tags: - OpenAI Compatible summary: Create Speech description: |- Generates audio from the input text. Returns the audio file content, or a stream of audio events. operationId: createSpeech requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateSpeechRequest' responses: '200': description: OK headers: Transfer-Encoding: schema: type: string description: chunked content: application/octet-stream: schema: type: string format: binary text/event-stream: schema: $ref: '#/components/schemas/CreateSpeechResponseStreamEvent' '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/GatewayError' '401': description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/GatewayError' '403': description: Permission denied content: application/json: schema: $ref: '#/components/schemas/GatewayError' '404': description: Not found content: application/json: schema: $ref: '#/components/schemas/GatewayError' '429': description: Rate limited content: application/json: schema: $ref: '#/components/schemas/GatewayError' 5XX: description: Server / upstream error content: application/json: schema: $ref: '#/components/schemas/GatewayError' components: schemas: CreateSpeechRequest: type: object additionalProperties: false properties: model: description: > One of the available [TTS models](https://developers.openai.com/api/docs/models#tts): `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`. anyOf: - type: string - type: string enum: - tts-1 - tts-1-hd - gpt-4o-mini-tts - gpt-4o-mini-tts-2025-12-15 input: type: string description: >- The text to generate audio for. The maximum length is 4096 characters. maxLength: 4096 instructions: type: string description: >- Control the voice of your generated audio with additional instructions. Does not work with `tts-1` or `tts-1-hd`. maxLength: 4096 voice: $ref: '#/components/schemas/VoiceIdsOrCustomVoice' description: >- The voice to use when generating the audio. Supported built-in voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, `verse`, `marin`, and `cedar`. You may also provide a custom voice object with an `id`, for example `{ "id": "voice_1234" }`. Previews of the voices are available in the [Text to speech guide](https://developers.openai.com/api/docs/guides/text-to-speech#voice-options). response_format: description: >- The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`. default: mp3 type: string enum: - mp3 - opus - aac - flac - wav - pcm speed: description: >- The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default. type: number default: 1 minimum: 0.25 maximum: 4 stream_format: description: >- The format to stream the audio in. Supported formats are `sse` and `audio`. `sse` is not supported for `tts-1` or `tts-1-hd`. type: string default: audio enum: - sse - audio required: - model - input - voice x-source: from: avs://openai/official authority: official CreateSpeechResponseStreamEvent: anyOf: - $ref: '#/components/schemas/SpeechAudioDeltaEvent' - $ref: '#/components/schemas/SpeechAudioDoneEvent' discriminator: propertyName: type x-source: from: avs://openai/official authority: official GatewayError: type: object description: | OpenAI-compatible error envelope. Top-level `error` object carrying `message` / `type` / `param` / `code`. `request_id` lives in the `X-Request-Id` response header, not in the body. The legacy `upstream` field is no longer emitted. x-source: from: gateway authority: gateway required: - error properties: error: type: object required: - message properties: message: type: string description: Human-readable error message. type: type: string nullable: true description: > Error category. OpenAI-compatible values include invalid_request_error / authentication_error / permission_error / not_found_error / rate_limit_error, etc. The upstream value is passed through verbatim; the enum is not fixed. param: type: string nullable: true description: Name of the offending field, when applicable. code: nullable: true description: | Sub-error code. May be a string or integer (the gateway treats `code` as an arbitrary type). VoiceIdsOrCustomVoice: title: Voice description: | A built-in voice name or a custom voice reference. anyOf: - $ref: '#/components/schemas/VoiceIdsShared' - type: object description: Custom voice reference. additionalProperties: false required: - id properties: id: type: string description: The custom voice ID, e.g. `voice_1234`. example: voice_1234 x-source: from: avs://openai/official authority: official SpeechAudioDeltaEvent: type: object description: Emitted for each chunk of audio data generated during speech synthesis. properties: type: type: string description: | The type of the event. Always `speech.audio.delta`. enum: - speech.audio.delta audio: type: string description: | A chunk of Base64-encoded audio data. required: - type - audio x-source: from: avs://openai/official authority: official SpeechAudioDoneEvent: type: object description: >- Emitted when the speech synthesis is complete and all audio has been streamed. properties: type: type: string description: | The type of the event. Always `speech.audio.done`. enum: - speech.audio.done usage: type: object description: | Token usage statistics for the request. properties: input_tokens: type: integer description: Number of input tokens in the prompt. output_tokens: type: integer description: Number of output tokens generated. total_tokens: type: integer description: Total number of tokens used (input + output). required: - input_tokens - output_tokens - total_tokens required: - type - usage x-source: from: avs://openai/official authority: official VoiceIdsShared: example: ash anyOf: - type: string - type: string enum: - alloy - ash - ballad - coral - echo - sage - shimmer - verse - marin - cedar x-source: from: avs://openai/official authority: official securitySchemes: gatewayBearer: type: http scheme: bearer bearerFormat: API Key description: | Gateway-issued API key, formatted as `sk-gateway-xxxxxxxx`. Used by OpenAI-shaped endpoints (/v1/chat/completions, etc.). x-source: from: gateway authority: gateway ````