> ## Documentation Index > Fetch the complete documentation index at: https://impossibl.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Synthesize speech from text > OpenAI-compatible text to speech. The response body is the raw audio. `voice` takes the provider's own voice ids, never OpenAI aliases; GET /v1/models lists the voices and endpoint for each speech model. Formats differ by model because the providers do. `xai/grok-voice-tts-1.0` encodes natively (mp3, wav, pcm) and bills $15.00 per 1M input characters, capped at 15,000 characters per request. `google/gemini-3.1-flash-tts-preview` emits 24 kHz mono PCM only, so it serves wav (a header over that PCM) and pcm, and bills tokens at $1.00/1M in and $20.00/1M out. ## OpenAPI ````yaml /openapi.yaml post /v1/audio/speech openapi: 3.1.0 info: title: Impossibl AI API version: 0.0.1 description: > The Impossibl AI API is one API for all AI providers, OpenAI-compatible across OpenAI, Anthropic, Google, xAI, and more (`GET /v1/models` lists the full catalog), billed from a prepaid credit balance. Provider usage is billed at provider list prices with no usage markup. Prepaid credit purchases charge a separate fixed 5% platform fee before tax. **Agent quickstart** 1. `POST /v1/accounts` — create a funded account; you get an API key and a signup-bonus balance in one call (no human step required). 2. Call `POST /v1/chat/completions`, `POST /v1/responses`, or `POST /v1/audio/transcriptions` with `Authorization: Bearer ` and a `provider/model` id from `GET /v1/models`. 3. Credits are deducted per request by token or audio-duration usage; check `GET /v1/account`. servers: - url: https://api.impossibl.com description: Production - url: http://localhost:8787 description: Local dev security: - BearerKey: [] paths: /v1/audio/speech: post: summary: Synthesize speech from text description: > OpenAI-compatible text to speech. The response body is the raw audio. `voice` takes the provider's own voice ids, never OpenAI aliases; GET /v1/models lists the voices and endpoint for each speech model. Formats differ by model because the providers do. `xai/grok-voice-tts-1.0` encodes natively (mp3, wav, pcm) and bills $15.00 per 1M input characters, capped at 15,000 characters per request. `google/gemini-3.1-flash-tts-preview` emits 24 kHz mono PCM only, so it serves wav (a header over that PCM) and pcm, and bills tokens at $1.00/1M in and $20.00/1M out. operationId: createSpeech requestBody: required: true content: application/json: schema: type: object required: - model - input - voice properties: model: type: string enum: - xai/grok-voice-tts-1.0 - google/gemini-3.1-flash-tts-preview input: type: string description: Text to speak. Both models accept inline expressive tags. voice: type: string description: A voice id the chosen model supports (see GET /v1/models). example: eve response_format: type: string enum: - mp3 - wav - pcm description: > Defaults to the model's native format: mp3 for xai, wav for google. A format the model cannot produce is a 400, never a substitution. speed: type: number minimum: 0.7 maximum: 1.5 default: 1 description: > Playback rate, xai/grok-voice-tts-1.0 only. Gemini has no rate control, so any value other than 1 is a 400 there rather than a silently ignored parameter. responses: '200': description: The synthesized audio. content: audio/mpeg: schema: type: string format: binary audio/wav: schema: type: string format: binary audio/pcm: schema: type: string format: binary '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/InsufficientCredits' '404': $ref: '#/components/responses/UnknownModel' '502': $ref: '#/components/responses/UpstreamError' '503': $ref: '#/components/responses/ProviderNotConfigured' components: responses: BadRequest: description: Malformed request (bad JSON, or missing required fields). content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: '`model` and `messages` are required' type: invalid_request_error Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Invalid API key type: authentication_error InsufficientCredits: description: The account's credit balance is empty. Top up to continue. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Insufficient credits. Top up to continue. type: insufficient_quota UnknownModel: description: The requested `model` id is not in the registry (see GET /v1/models). content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'Unknown model: foo/bar' type: invalid_request_error UpstreamError: description: The upstream provider returned an error. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'permission-denied: ...' type: upstream_error ProviderNotConfigured: description: The provider for this model has no API key configured on the gateway. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'Provider not configured: missing OPENAI_API_KEY' type: provider_not_configured schemas: Error: type: object properties: error: type: object properties: message: type: string type: type: string description: >- One of authentication_error, invalid_request_error, insufficient_quota, upstream_error, provider_not_configured. securitySchemes: BearerKey: type: http scheme: bearer description: Gateway API key (`imp-rt-...`) from POST /v1/accounts or /v1/keys. ````