> ## Documentation Index > Fetch the complete documentation index at: https://platform.perso.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Stream Text to Speech > Convert text to speech with streaming response for real-time playback. ## Prerequisites You must have at least one cloned voice. Use **Create Voice** (`POST /v1/voices/add`) to create a voice, then retrieve its `voice_id` from **List Voices** (`GET /v2/voices`). Authenticate using the `PersoPlatform-APIKey` header. ``` --header 'PersoPlatform-APIKey: ' ``` ## URL Path Parameters Replace `{voice_id}` in the URL with your voice ID. Retrieve available voice IDs from **List Voices** (`GET /v2/voices`). ``` POST /v1/text-to-speech/{voice_id}/stream ``` ## Request Parameters | Parameter | Required | Description | |-----------|----------|-------------| | `text` | Yes | Text to convert to speech | | `model_id` | No | Default: `perso_multilingual_v1` | ## Query Parameters | Parameter | Required | Description | |-----------|----------|-------------| | `output_format` | Yes | Audio format for streaming. Default: `wav_24000` (see formats below) | ## How It Works Audio chunks are streamed as they are generated, enabling: - Lower latency for first audio - Real-time playback during generation - Reduced memory usage for long text ## Example Select **"TextToSpeechStreamRequest"** from the **Examples** dropdown to see a request example. ```bash curl -X POST "https://platform.perso.ai/api/speech/v1/text-to-speech/{voice_id}/stream?output_format=mp3_44100_192" -H "PersoPlatform-APIKey: " -H "Content-Type: application/json" -H "Accept: */*" -d '{"text": "Hello, this is a streaming test."}' --output audio.mp3 ``` ## OpenAPI ````yaml /specs/openapi-speech.json post /api/speech/v1/text-to-speech/{voice_id}/stream openapi: 3.0.3 info: title: Perso Speech API version: 0.0.0 servers: - url: https://platform.perso.ai security: [] paths: /api/speech/v1/text-to-speech/{voice_id}/stream: post: tags: - Speech summary: Stream Text to Speech description: > Convert text to speech with streaming response for real-time playback. ## Prerequisites You must have at least one cloned voice. Use **Create Voice** (`POST /v1/voices/add`) to create a voice, then retrieve its `voice_id` from **List Voices** (`GET /v2/voices`). Authenticate using the `PersoPlatform-APIKey` header. ``` --header 'PersoPlatform-APIKey: ' ``` ## URL Path Parameters Replace `{voice_id}` in the URL with your voice ID. Retrieve available voice IDs from **List Voices** (`GET /v2/voices`). ``` POST /v1/text-to-speech/{voice_id}/stream ``` ## Request Parameters | Parameter | Required | Description | |-----------|----------|-------------| | `text` | Yes | Text to convert to speech | | `model_id` | No | Default: `perso_multilingual_v1` | ## Query Parameters | Parameter | Required | Description | |-----------|----------|-------------| | `output_format` | Yes | Audio format for streaming. Default: `wav_24000` (see formats below) | ## How It Works Audio chunks are streamed as they are generated, enabling: - Lower latency for first audio - Real-time playback during generation - Reduced memory usage for long text ## Example Select **"TextToSpeechStreamRequest"** from the **Examples** dropdown to see a request example. ```bash curl -X POST "https://platform.perso.ai/api/speech/v1/text-to-speech/{voice_id}/stream?output_format=mp3_44100_192" -H "PersoPlatform-APIKey: " -H "Content-Type: application/json" -H "Accept: */*" -d '{"text": "Hello, this is a streaming test."}' --output audio.mp3 ``` operationId: speech_v1_text_to_speech_stream_create parameters: - in: query name: output_format schema: type: string enum: - mp3_44100 - pcm_24000 - pcm_44100 - wav_24000 - wav_44100 default: wav_24000 description: The desired audio output format. required: true - in: path name: voice_id schema: type: string description: >- The ID of the voice to use for speech generation. Retrieve available voice IDs from **List Voices** (`GET /v2/voices`). required: true requestBody: content: application/json: schema: $ref: '#/components/schemas/TextToSpeechStreamRequestBodyRequest' examples: TextToSpeechStreamRequest: value: text: Hello, this is a streaming text to speech test. model_id: perso_multilingual_v1 required: true responses: '200': content: '*/*': schema: type: string format: binary description: >- Streaming audio binary. Content-Type depends on `output_format`: `audio/wav`, `audio/mpeg`, or `audio/L16`. '400': description: Bad Request - Invalid input data or parameters. '401': description: Unauthorized - Invalid or missing authentication credentials. '403': description: Forbidden - You do not have permission to perform this action. '404': description: Not Found - The requested resource could not be found. '500': description: Internal Server Error - An unexpected error occurred. security: - PersoPlatform-APIKey: [] xi-api-key: [] - {} components: schemas: TextToSpeechStreamRequestBodyRequest: type: object properties: text: type: string minLength: 1 description: Text to synthesize and stream as speech. maxLength: 5000 model_id: type: string minLength: 1 default: perso_multilingual_v1 voice_settings: type: object additionalProperties: {} description: >- Optional dict of voice tuning parameters (e.g. `stability`, `similarity_boost`) compatible with ElevenLabs voice settings. required: - text securitySchemes: PersoPlatform-APIKey: type: apiKey in: header name: PersoPlatform-APIKey xi-api-key: type: apiKey in: header name: xi-api-key description: >- Use this header if you want to call the API with an ElevenLabs-compatible SDK. Pass your Perso API key as the `xi-api-key` header value. ````