> ## Documentation Index > Fetch the complete documentation index at: https://docs.sunbird.ai/llms.txt > Use this file to discover all available pages before exploring further. # Synthesize Speech (Orpheus-3B) > Calls the Orpheus-3B Modal vLLM inference app, uploads the generated WAV to Google Cloud Storage, and returns a v4 presigned download URL valid for the configured expiry window (default 30 minutes), together with metadata and stage-by-stage latency timings. ## OpenAPI ````yaml api-reference/openapi-legacy.json POST /tasks/modal/orpheus/tts openapi: 3.1.0 info: title: Sunbird AI API (Legacy / Deprecated) description: > Welcome to the Sunbird AI API documentation. The Sunbird AI API provides access to Sunbird's language models and AI services for Ugandan languages. ## Supported Languages **English**, **Acholi**, **Ateso**, **Luganda**, **Lugbara**, **Runyankole**, **Swahili** and **20+** more Ugandan languages supported via sunflower. ## Getting Started You can checkout the [usage guide](https://salt.sunbird.ai/API/) for a full tutorial. For quickstart tutorials, visit our [GitHub repository](https://github.com/SunbirdAI/sunbird-ai-api/blob/main/docs/tutorial.md) ### Authentication #### Signing Up If you don't already have an account, use the `/auth/register` endpoint to create one. #### Getting an Access Token Authentication is done via a Bearer token. Use the `/auth/token` endpoint to get your access token. This token lasts for 7 days. Use the `Authorize` button below to login and access the protected endpoints. ## API Endpoints ### Translation - **`POST /tasks/translate`** - Translate text between 32 Ugandan and East African languages using the Sunflower model. Languages are accepted as ISO codes (`lug`) or full names (`Luganda`); `source_language` is optional (auto-detected when omitted). Translation works between any pair of supported languages. ### Language Detection - **`POST /tasks/language_id`** - Auto-detect the language of text input (supports Acholi, Ateso, English, Luganda, Lugbara, Runyankole) ### Speech-to-Text (STT) - **`POST /tasks/audio/transcriptions`** - Unified STT endpoint (OpenAI-style). - Accepts an uploaded audio file (`audio`) or a GCS object (`gcs_blob_name`). - `platform`: `modal` (default, Whisper large-v3) or `runpod`. - RunPod options: `adapter` (language adapter), `whisper`, `recognise_speakers` (diarization), and the `org` organization workflow. - `language`: 3-letter code (e.g. `eng`, `lug`) or full name; improves accuracy. Supports WAV, MP3, OGG, M4A, and more. Auto-detects when omitted. - **Deprecated** → use `POST /tasks/audio/transcriptions`: - `POST /tasks/stt`, `POST /tasks/stt_from_gcs`, `POST /tasks/org/stt`, `POST /tasks/modal/stt` ### Text-to-Speech (TTS) - **`POST /tasks/audio/speech`** - Unified single-synthesis endpoint. - `model`: `orpheus-3b-tts` (default) or `spark-tts`; `platform`: `modal` or `runpod`. - `voice`: speaker tag/name. `response_mode`: `url` (default), `stream`, or `both` (`stream`/`both` require `spark-tts` on `modal`). - Orpheus tuning: `language`, `temperature`, `top_p`, `repetition_penalty`, `max_tokens`, `seed`. Returns a signed GCP Storage URL. - **`POST /tasks/audio/speech/batch`** - Batch synthesis (orpheus-3b-tts only), 1-128 items. - **`GET /tasks/voice/speakers`** - List voices for a `model` (optional orpheus `language`). - **orpheus-3b-tts** covers 20 African languages: Acholi (`ach`), Afrikaans (`afr`), English (`eng`), Ewe (`ewe`), Fulah (`ful`), Hausa (`hau`), Igbo (`ibo`), Kikuyu (`kik`), Kinyarwanda (`kin`), Lugbara (`lgg`), Lingala (`lin`), Luganda (`lug`), Luo (`luo`), Runyankole (`nyn`), Sesotho (`sot`), Swahili (`swa`), Ateso (`teo`), Setswana (`tsn`), Xhosa (`xho`), Yoruba (`yor`). A few (`lgg`, `sot`, `tsn`) are in the training mix but expose no individual voice IDs yet. Full per-speaker catalog: see the [tutorial](https://github.com/SunbirdAI/sunbird-ai-api/blob/main/docs/tutorial.md) or call `GET /tasks/voice/speakers`. - **`GET /tasks/audio/speech/url`** - Refresh an expired signed URL for a stored audio object. - **Deprecated** → superseded by the unified endpoints above: - `POST /tasks/modal/tts`, `POST /tasks/runpod/tts`, `POST /tasks/modal/orpheus/tts` → `POST /tasks/audio/speech` - `POST /tasks/modal/tts/stream` → `/tasks/audio/speech` (`response_mode=stream`) - `POST /tasks/modal/tts/stream-with-url` → `/tasks/audio/speech` (`response_mode=both`) - `POST /tasks/modal/orpheus/tts/batch` → `POST /tasks/audio/speech/batch` - `GET /tasks/modal/tts/speakers`, `GET /tasks/modal/orpheus/speakers`, `GET /tasks/modal/orpheus/speakers/{language}` → `GET /tasks/voice/speakers` - `GET /tasks/modal/tts/refresh-url` → `GET /tasks/audio/speech/url` ### Inference (Sunflower Chat) - **`POST /tasks/chat/completions`** - OpenAI-compatible chat completions (Sunflower model). Supports single instructions, multi-turn conversations, and SSE streaming (`stream: true`). Use model `Sunbird/Sunflower-14B`. - **Deprecated** → superseded by the unified endpoint above: - `POST /tasks/sunflower_inference` → `POST /tasks/chat/completions` - `POST /tasks/sunflower_simple` → `POST /tasks/chat/completions` (send the instruction as a single user message) ### File Upload - **`POST /tasks/generate-upload-url`** - Generate signed URLs for direct client uploads to GCP Storage - Supports audio files, images, and other content types - Includes path traversal protection and input validation - Returns temporary signed URL valid for 30 minutes ### WhatsApp Integration (Webhooks) - **`POST /tasks/webhook`** - Handle incoming WhatsApp Business API messages - **`GET /tasks/webhook`** - Verify webhook endpoint ownership for WhatsApp ### Legacy Endpoints - **`POST /tasks/summarise`** - *(Deprecated)* Anonymized text summarization (use Sunflower inference instead) ## Rate Limiting API endpoints are rate-limited to ensure fair usage. Authentication is required for most endpoints. version: 0.1.0 servers: - url: https://api.sunbird.ai security: [] tags: - name: legacy/deprecated description: >- Deprecated endpoints retained for backward compatibility. Each is superseded by a unified endpoint — see its Deprecation/Sunset/Link response headers — and will be removed after the sunset date. Do not build new integrations against these. paths: /tasks/modal/orpheus/tts: post: tags: - legacy/deprecated summary: Synthesize speech for one input via Orpheus-3B description: >- Calls the Orpheus-3B Modal vLLM inference app, uploads the generated WAV to Google Cloud Storage, and returns a v4 presigned download URL valid for the configured expiry window (default 30 minutes), together with metadata and stage-by-stage latency timings. operationId: synthesize_tts_tasks_modal_orpheus_tts_post requestBody: content: application/json: schema: $ref: '#/components/schemas/OrpheusTTSRequest' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/OrpheusTTSResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' deprecated: true security: - OAuth2PasswordBearer: [] components: schemas: OrpheusTTSRequest: properties: text: type: string maxLength: 2000 minLength: 1 title: Text description: Text to synthesize. speaker_id: type: string title: Speaker Id description: Speaker tag from the Orpheus finetune set (see GET /speakers). default: salt_lug_0001 language: anyOf: - type: string - type: 'null' title: Language description: >- Optional ISO 639-3 language code (e.g. 'lug', 'eng'). If set, speaker_id must belong to it. seed: anyOf: - type: integer - type: 'null' title: Seed description: RNG seed for reproducibility. temperature: type: number maximum: 2 minimum: 0 title: Temperature default: 0.6 top_p: type: number maximum: 1 exclusiveMinimum: 0 title: Top P default: 0.95 repetition_penalty: type: number maximum: 2 minimum: 1 title: Repetition Penalty default: 1.1 max_tokens: type: integer maximum: 4096 minimum: 64 title: Max Tokens default: 1200 type: object required: - text title: OrpheusTTSRequest OrpheusTTSResponse: properties: audio_url: type: string maxLength: 2083 minLength: 1 format: uri title: Audio Url audio_url_expires_at: type: string format: date-time title: Audio Url Expires At speaker_id: type: string title: Speaker Id language: anyOf: - type: string - type: 'null' title: Language sample_rate: type: integer title: Sample Rate default: 24000 duration_seconds: type: number title: Duration Seconds chunks: anyOf: - type: integer - type: 'null' title: Chunks audio_size_bytes: type: integer title: Audio Size Bytes gcs_object: type: string title: Gcs Object request_id: type: string title: Request Id timings_ms: $ref: '#/components/schemas/OrpheusTimings' type: object required: - audio_url - audio_url_expires_at - speaker_id - duration_seconds - audio_size_bytes - gcs_object - request_id - timings_ms title: OrpheusTTSResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError OrpheusTimings: properties: inference_ms: type: number title: Inference Ms upload_ms: type: number title: Upload Ms signed_url_ms: type: number title: Signed Url Ms total_ms: type: number title: Total Ms type: object required: - inference_ms - upload_ms - signed_url_ms - total_ms title: OrpheusTimings ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: OAuth2PasswordBearer: type: oauth2 flows: password: scopes: {} tokenUrl: /auth/token ````