{ "openapi": "3.1.0", "info": { "title": "Runware API - Seed Audio 1.0", "summary": "Versatile speech generation model for expressive TTS, voice conversion, and speech editing", "description": "Seed Audio 1.0 is a ByteDance speech generation model built for high-quality, highly controllable audio output. Public technical materials describe the underlying Seed-TTS family as supporting zero-shot text-to-speech, cross-lingual speech generation, emotion control, speaker adaptation, voice conversion, speech editing, and speed editing, making it well suited to narration, dubbing, character voice work, and other expressive speech workflows.", "version": "1.0.0", "x-model-id": "bytedance-seed-audio-1-0", "x-air-id": "bytedance:seed-audio@1.0", "x-status": "live", "x-creator": { "id": "bytedance", "name": "ByteDance", "logo": "https://assets.runware.ai/a370f11f-f8f3-4af2-b0dc-755bac69f620.png" }, "x-capabilities": [ "text-to-audio", "audio-to-audio", "checkpoint" ], "x-released-at": "2024-06-04T00:00:00Z", "x-cover-image": "https://assets.runware.ai/covers/bytedance-seed-audio-1-0.jpg", "x-pricing": { "overview": "Pricing is $0.158 per min of Audio generated", "examples": [ { "configuration": "1min", "price": "$0.158" } ] } }, "servers": [ { "url": "https://api.runware.ai/v1", "description": "Runware REST API" } ], "components": { "securitySchemes": { "apiKeyAuth": { "type": "http", "scheme": "bearer", "description": "Runware API Key (e.g., Bearer )" } }, "schemas": { "AuthenticationTask": { "title": "Authentication", "description": "Authenticates a connection using an API key. Can be sent as the first element of the request array as an alternative to using the Authorization header.", "type": "object", "x-response-schema": "https://schemas.runware.ai/responses/utilities/authentication.json", "properties": { "taskType": { "$id": "https://schemas.runware.ai/requests/parameters/api/task-type.json", "title": "Task Type", "description": "Identifier for the type of task being performed", "type": "string", "const": "authentication" }, "apiKey": { "$id": "https://schemas.runware.ai/requests/parameters/authentication/api-key.json", "title": "API Key", "description": "Your Runware API key.", "type": "string" }, "connectionSessionUUID": { "$id": "https://schemas.runware.ai/requests/parameters/authentication/connection-session-uuid.json", "title": "Connection Session UUID", "description": "Optional session UUID to resume a previous connection and receive any buffered results.", "type": "string", "format": "uuid" } }, "required": [ "taskType", "apiKey" ], "additionalProperties": false }, "RequestBody": { "type": "array", "items": { "type": "object", "properties": { "model": { "title": "Model", "description": "Identifier of the model to use for generation.", "type": "string", "const": "bytedance:seed-audio@1.0" }, "inputs": { "title": "Inputs", "description": "The unified payload wrapper for complex media assets dictating image, video or audio inference constraints.", "type": "object", "properties": { "referenceImages": { "title": "Reference Images", "description": "List of reference images (UUID, URL, Data URI, or Base64). A single character image whose appearance conditions the generated voice.", "type": "array", "minItems": 1, "items": { "title": "Image", "description": "Image input (UUID, URL, Data URI, or Base64).", "type": "string", "anyOf": [ { "format": "uuid" }, { "format": "uri" }, { "pattern": "^data:image\\/[a-zA-Z]+;base64,[a-zA-Z0-9+/=]+$" }, { "pattern": "^[a-zA-Z0-9+/=]+$" } ] }, "maxItems": 1 }, "referenceAudios": { "title": "Reference Audios", "description": "List of reference audios (UUID, URL). Reference clips that condition the generated voice and emotion.", "type": "array", "minItems": 1, "items": { "title": "Audio", "description": "Audio input (UUID or URL).", "type": "string", "anyOf": [ { "format": "uuid" }, { "format": "uri" } ] }, "maxItems": 3 } }, "additionalProperties": false }, "positivePrompt": { "title": "Positive Prompt", "description": "Text prompt describing the voice, environment, background music, sound effects, and dialogue to synthesize. In audio-reference mode, reference clips in array order as `@Audio1`, `@Audio2`, and `@Audio3`.", "type": "string", "maxLength": 2048 }, "speech": { "title": "Speech", "description": "Settings for speech generation.", "type": "object", "properties": { "volume": { "title": "Volume", "description": "Volume level of the generated speech. `100` produces 2.0x volume, `0` leaves volume unchanged, and `-50` produces 0.5x volume.", "type": "integer", "multipleOf": 1, "minimum": -50, "maximum": 100, "default": 0 }, "speed": { "title": "Speed", "description": "Playback speed of the generated speech. `100` produces 2.0x speed, `0` is the normal rate, and `-50` produces 0.5x speed.", "type": "integer", "multipleOf": 1, "minimum": -50, "maximum": 100, "default": 0 }, "pitch": { "title": "Pitch", "description": "Pitch adjustment for the voice.", "type": "integer", "multipleOf": 1, "minimum": -12, "maximum": 12, "default": 0 } }, "additionalProperties": false }, "taskType": { "title": "Task Type", "description": "Identifier for the type of task being performed", "type": "string", "const": "audioInference" }, "taskUUID": { "title": "Task UUID", "description": "UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.", "type": "string", "format": "uuid" }, "webhookURL": { "title": "Webhook URL", "description": "Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.", "type": "string", "format": "uri" }, "includeCost": { "title": "Include Cost", "description": "Include task cost in the response.", "type": "boolean", "default": false }, "numberResults": { "title": "Number of Results", "description": "Number of results to generate. Each result uses a different seed, producing variations of the same parameters.", "type": "integer", "minimum": 1, "default": 1, "maximum": 4 }, "uploadEndpoint": { "title": "Upload Endpoint", "description": "Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.\n\n**Common use cases:**\n\n- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.\n- **CDN integration**: Upload to content delivery networks for immediate distribution.\n\n```text\n// S3 presigned URL for secure upload\nhttps://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600\n\n// Google Cloud Storage presigned URL\nhttps://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789\n\n// Custom storage endpoint\nhttps://storage.example.com/uploads/generated-image.jpg\n```\n\nThe content data will be sent as the request body to the specified URL when generation is complete.\n\n[Read full documentation](https://runware.ai/docs/models/bytedance-seed-audio-1-0#uploadEndpoint)", "type": "string", "format": "uri" }, "ttl": { "title": "TTL", "description": "Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.", "type": "integer", "minimum": 60 }, "outputType": { "title": "Output Type", "description": "Audio output type.", "type": "string", "enum": [ "URL", "base64Data", "dataURI" ], "default": "URL" }, "outputFormat": { "title": "Output Format", "description": "Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.\n\n- \\`JPG\\`: Best for photorealistic images with smaller file sizes (no transparency).\n- \\`PNG\\`: Lossless compression, supports high quality and transparency (alpha channel).\n- \\`WEBP\\`: Modern format providing superior compression and transparency support.\n- \\`MP4\\`: Widely supported video container (H.264), recommended for general use.\n- \\`WEBM\\`: Optimized for web delivery.\n- \\`MOV\\`: QuickTime format, common in professional workflows (Apple ecosystem).\n- \\`GIF\\`: Animated image format (no audio), suitable for short loops or previews.\n- \\`MP3\\`: Compressed audio, smaller file size.\n- \\`WAV\\`: Uncompressed, high-quality audio.\n- \\`FLAC\\`: Lossless compression.\n- \\`OGG\\`: Open-source compressed audio format (Vorbis codec).\n- \\`SVG\\`: Scalable Vector Graphics.\n- \\`TIFF\\`: High-quality output supporting layers.\n- \\`GLB\\`: Binary glTF format for 3D models, including geometry, textures, and PBR materials.\n\n> [!NOTE]\n> \\*\\*Transparency\\*\\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \\`PNG\\`, \\`WEBP\\`, \\`TIFF\\`). \\`JPG\\` does not support transparency.\n\n[Read full documentation](https://runware.ai/docs/models/bytedance-seed-audio-1-0#outputFormat)", "type": "string", "enum": [ "MP3", "WAV", "FLAC", "OGG" ], "default": "MP3" }, "deliveryMethod": { "title": "Delivery Method", "description": "Determines how the API delivers task results.", "type": "string", "oneOf": [ { "const": "sync", "description": "Returns complete results directly in the API response." }, { "const": "async", "description": "Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse." } ], "default": "sync" }, "audioSettings": { "title": "Audio Settings", "description": "Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (`MP3` and `OGG`). When using lossless formats (`WAV` or `FLAC`), this parameter must not be provided.\n\nThe available sample rates and valid bitrate ranges depend on the output format. For `OGG`, bitrate limits also vary by the number of channels.\n\n**MP3 bitrate limits**:\n\nBitrate limits for MP3 are the same regardless of mono or stereo.\n\n| Sample Rate | Min Bitrate | Max Bitrate |\n| --- | --- | --- |\n| 8,000 Hz | 8 kbps | 64 kbps |\n| 11,025 Hz | 8 kbps | 64 kbps |\n| 12,000 Hz | 8 kbps | 64 kbps |\n| 16,000 Hz | 8 kbps | 160 kbps |\n| 22,050 Hz | 8 kbps | 160 kbps |\n| 24,000 Hz | 8 kbps | 160 kbps |\n| 32,000 Hz | 32 kbps | 320 kbps |\n| 44,100 Hz | 32 kbps | 320 kbps |\n| 48,000 Hz | 32 kbps | 320 kbps |\n\n**OGG bitrate limits — Mono (1 channel)**:\n\n| Sample Rate | Min Bitrate | Max Bitrate |\n| --- | --- | --- |\n| 8,000 Hz | 8 kbps | 40 kbps |\n| 12,000 Hz | 16 kbps | 48 kbps |\n| 16,000 Hz | 16 kbps | 96 kbps |\n| 24,000 Hz | 16 kbps | 80 kbps |\n| 48,000 Hz | 32 kbps | 224 kbps |\n\n**OGG bitrate limits — Stereo (2 channels)**:\n\n| Sample Rate | Min Bitrate | Max Bitrate |\n| --- | --- | --- |\n| 8,000 Hz | 16 kbps | 80 kbps |\n| 12,000 Hz | 16 kbps | 96 kbps |\n| 16,000 Hz | 24 kbps | 192 kbps |\n| 24,000 Hz | 32 kbps | 160 kbps |\n| 48,000 Hz | 48 kbps | 256 kbps |\n\n> [!NOTE]\n> **Lossless formats**: When `outputFormat` is set to `WAV` or `FLAC`, the `audioSettings` parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.\n\n[Read full documentation](https://runware.ai/docs/models/bytedance-seed-audio-1-0#audioSettings)", "type": "object", "properties": { "bitrate": { "title": "Bitrate", "description": "Audio bitrate in kbps.", "type": "integer", "minimum": 8 }, "channels": { "title": "Channels", "description": "Number of audio channels. 1 for mono, 2 for stereo.", "type": "integer", "enum": [ 1, 2 ], "default": 2 }, "sampleRate": { "title": "Sample Rate", "description": "Audio sample rate in Hz.", "type": "integer" } }, "additionalProperties": false } }, "required": [ "positivePrompt", "taskType", "taskUUID", "model" ], "allOf": [ { "if": { "properties": { "outputFormat": { "enum": [ "WAV", "FLAC" ] } }, "required": [ "outputFormat" ] }, "then": { "not": { "required": [ "audioSettings" ] } } }, { "if": { "properties": { "outputFormat": { "const": "MP3" } }, "required": [ "outputFormat" ] }, "then": { "properties": { "audioSettings": { "properties": { "sampleRate": { "enum": [ 8000, 11025, 12000, 16000, 22050, 24000, 32000, 44100, 48000 ] } } } }, "allOf": [ { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "enum": [ 8000, 11025, 12000 ] } }, "required": [ "sampleRate" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 8, "maximum": 64 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "enum": [ 16000, 22050, 24000 ] } }, "required": [ "sampleRate" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 8, "maximum": 160 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "enum": [ 32000, 44100, 48000 ] } }, "required": [ "sampleRate" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 32, "maximum": 320 } } } } } } ] } }, { "if": { "properties": { "outputFormat": { "const": "OGG" } }, "required": [ "outputFormat" ] }, "then": { "properties": { "audioSettings": { "properties": { "sampleRate": { "enum": [ 8000, 12000, 16000, 24000, 48000 ] } } } }, "allOf": [ { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 8000 }, "channels": { "const": 1 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 8, "maximum": 40 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 8000 }, "channels": { "const": 2 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 16, "maximum": 80 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 12000 }, "channels": { "const": 1 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 16, "maximum": 48 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 12000 }, "channels": { "const": 2 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 16, "maximum": 96 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 16000 }, "channels": { "const": 1 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 16, "maximum": 96 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 16000 }, "channels": { "const": 2 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 24, "maximum": 192 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 24000 }, "channels": { "const": 1 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 16, "maximum": 80 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 24000 }, "channels": { "const": 2 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 32, "maximum": 160 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 48000 }, "channels": { "const": 1 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 32, "maximum": 224 } } } } } }, { "if": { "properties": { "audioSettings": { "properties": { "sampleRate": { "const": 48000 }, "channels": { "const": 2 } }, "required": [ "sampleRate", "channels" ] } }, "required": [ "audioSettings" ] }, "then": { "properties": { "audioSettings": { "properties": { "bitrate": { "minimum": 48, "maximum": 256 } } } } } } ] } }, { "not": { "allOf": [ { "properties": { "inputs": { "required": [ "referenceAudios" ] } }, "required": [ "inputs" ] }, { "properties": { "inputs": { "required": [ "referenceImages" ] } }, "required": [ "inputs" ] } ] } } ], "additionalProperties": false }, "description": "You must always POST an array of task objects." }, "ResponseBody": { "type": "object", "properties": { "data": { "type": "array", "items": { "type": "object", "description": "Unknown response structure" } } } }, "ErrorResponse": { "title": "Error Response", "description": "Standard error response returned by the Runware API.", "type": "object", "properties": { "errors": { "type": "array", "items": { "type": "object", "required": [ "code", "message" ], "additionalProperties": true, "properties": { "code": { "type": "string", "description": "A short identifier for the error (e.g., invalidApiKey, timeoutProvider)." }, "message": { "type": "string", "description": "A human-readable explanation of what went wrong." }, "parameter": { "type": "string", "description": "The request parameter related to the error, if applicable." }, "taskType": { "type": "string", "description": "The task type of the request that failed." }, "taskUUID": { "type": "string", "description": "The unique identifier of the failed request." }, "documentation": { "type": "string", "description": "A link to relevant documentation." } } } } }, "required": [ "errors" ], "additionalProperties": false } } }, "paths": { "/": { "post": { "summary": "Run Seed Audio 1.0", "description": "Seed Audio 1.0 is a ByteDance speech generation model built for high-quality, highly controllable audio output. Public technical materials describe the underlying Seed-TTS family as supporting zero-shot text-to-speech, cross-lingual speech generation, emotion control, speaker adaptation, voice conversion, speech editing, and speed editing, making it well suited to narration, dubbing, character voice work, and other expressive speech workflows.", "operationId": "run_bytedance_seed_audio_1_0", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/RequestBody" } } } }, "responses": { "200": { "description": "Successful response", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ResponseBody" } } } }, "400": { "description": "Bad Request — Missing or invalid parameters.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "401": { "description": "Unauthorized — No valid API key provided.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "402": { "description": "Payment Required — Insufficient account balance.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "403": { "description": "Forbidden — The API key lacks permissions for this request.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "429": { "description": "Too Many Requests — Rate limit exceeded.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "500": { "description": "Server Error — Something went wrong on Runware's end.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Service Unavailable — Temporarily unavailable (maintenance or capacity).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } } }, "security": [ { "apiKeyAuth": [] } ] }