> ## Documentation Index > Fetch the complete documentation index at: https://developers.telnyx.com/llms.txt > Use this file to discover all available pages before exploring further. # Create a voice clone from an audio file upload > Creates a new voice clone by uploading an audio file directly. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best results, provide 5–10 seconds of clear speech. Maximum file size: 5MB for Telnyx, 20MB for Minimax. ## OpenAPI ````yaml /openapi/generated/text-to-speech/voice-designs.yml post /voice_clones/from_upload openapi: 3.1.0 info: contact: email: support@telnyx.com description: >- Design AI-generated voices using natural language prompts, manage voice versions, and capture voice identities as clones for use in text-to-speech synthesis. title: Voice Designs and Voice Clones API version: 2.0.0 servers: - url: https://api.telnyx.com/v2 security: - bearerAuth: [] tags: - description: >- Create and manage AI-generated voice designs using natural language prompts. name: Voice Designs - description: >- Capture and manage voice identities as clones for use in text-to-speech synthesis. name: Voice Clones paths: /voice_clones/from_upload: post: tags: - Voice Clones summary: Create a voice clone from an audio file upload description: >- Creates a new voice clone by uploading an audio file directly. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best results, provide 5–10 seconds of clear speech. Maximum file size: 5MB for Telnyx, 20MB for Minimax. operationId: createVoiceCloneFromUpload requestBody: required: true content: multipart/form-data: schema: $ref: '#/components/schemas/VoiceCloneUploadRequest' responses: '201': description: Voice clone created successfully from the uploaded audio. content: application/json: schema: $ref: '#/components/schemas/VoiceCloneResponse' '202': description: >- Voice clone accepted — on-prem import in progress (Ultra model). Poll GET /voice_clones/{id} to check status. content: application/json: schema: $ref: '#/components/schemas/VoiceCloneResponse' '400': description: >- Bad request — the audio file is invalid, unsupported, or exceeds the size limit. content: application/json: schema: $ref: '#/components/schemas/voice-designs_ErrorResponse' '401': description: Unauthorized — missing or invalid bearer token. content: application/json: schema: $ref: '#/components/schemas/voice-designs_ErrorResponse' '422': description: Unprocessable entity — validation error in the request body. content: application/json: schema: $ref: '#/components/schemas/voice-designs_ErrorResponse' '502': description: Bad gateway — upstream voice cloning service is unavailable. content: application/json: schema: $ref: '#/components/schemas/voice-designs_ErrorResponse' x-codeSamples: - lang: JavaScript source: |- import Telnyx from 'telnyx'; const client = new Telnyx({ apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted }); const response = await client.voiceClones.createFromUpload({ params: { audio_file: fs.createReadStream('path/to/file'), gender: 'male', language: 'lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf', name: 'name', provider: 'telnyx', }, }); console.log(response.data); - lang: Python source: |- import os from telnyx import Telnyx client = Telnyx( api_key=os.environ.get("TELNYX_API_KEY"), # This is the default and can be omitted ) response = client.voice_clones.create_from_upload( params={ "audio_file": b"Example data", "gender": "male", "language": "lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf", "name": "name", "provider": "telnyx", }, ) print(response.data) - lang: Go source: "package main\n\nimport (\n\t\"bytes\"\n\t\"context\"\n\t\"fmt\"\n\t\"io\"\n\n\t\"github.com/team-telnyx/telnyx-go\"\n\t\"github.com/team-telnyx/telnyx-go/option\"\n)\n\nfunc main() {\n\tclient := telnyx.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tresponse, err := client.VoiceClones.NewFromUpload(context.TODO(), telnyx.VoiceCloneNewFromUploadParams{\n\t\tOfTelnyxQwen3TtsClone: &telnyx.VoiceCloneNewFromUploadParamsParamsTelnyxQwen3TtsClone{\n\t\t\tAudioFile: io.Reader(bytes.NewBuffer([]byte(\"Example data\"))),\n\t\t\tGender: \"male\",\n\t\t\tLanguage: \"lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf\",\n\t\t\tName: \"name\",\n\t\t\tProvider: \"telnyx\",\n\t\t},\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", response.Data)\n}\n" - lang: Java source: >- package com.telnyx.sdk.example; import com.telnyx.sdk.client.TelnyxClient; import com.telnyx.sdk.client.okhttp.TelnyxOkHttpClient; import com.telnyx.sdk.models.voiceclones.VoiceCloneCreateFromUploadParams; import com.telnyx.sdk.models.voiceclones.VoiceCloneCreateFromUploadResponse; import java.io.ByteArrayInputStream; public final class Main { private Main() {} public static void main(String[] args) { TelnyxClient client = TelnyxOkHttpClient.fromEnv(); VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone params = VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone.builder() .audioFile(new ByteArrayInputStream("Example data".getBytes())) .gender(VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone.Gender.MALE) .language("lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf") .name("name") .provider(VoiceCloneCreateFromUploadParams.Params.TelnyxQwen3TtsClone.Provider.TELNYX) .build(); VoiceCloneCreateFromUploadResponse response = client.voiceClones().createFromUpload(params); } } - lang: Ruby source: |- require "telnyx" telnyx = Telnyx::Client.new(api_key: "My API Key") response = telnyx.voice_clones.create_from_upload( params: { audio_file: StringIO.new("Example data"), gender: :male, language: "lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf", name: "name", provider: :telnyx } ) puts(response) - lang: PHP source: >- voiceClones->createFromUpload( params: [ 'audioFile' => FileParam::fromString('Example data', filename: uniqid('file-upload-', true)), 'gender' => 'male', 'language' => 'lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf', 'name' => 'name', 'provider' => 'telnyx', 'label' => 'label', 'modelID' => 'Qwen3TTS', 'refText' => 'ref_text', ], ); var_dump($response); } catch (APIException $e) { echo $e->getMessage(); } - lang: CLI source: |- telnyx voice-clones create-from-upload \ --api-key 'My API Key' \ --params '{audio_file: Example data, gender: male, language: lkf-Lz1vLbBu-9uDh-9AHaOS2D-Cbf, name: name, provider: telnyx}' components: schemas: VoiceCloneUploadRequest: description: >- Multipart form data for creating a voice clone from a direct audio upload. Maximum file size: 5MB for Telnyx, 20MB for Minimax. oneOf: - $ref: '#/components/schemas/TelnyxQwen3TTSClone' - $ref: '#/components/schemas/TelnyxUltraClone' - $ref: '#/components/schemas/MinimaxClone' VoiceCloneResponse: type: object description: Response envelope for a single voice clone. properties: data: $ref: '#/components/schemas/VoiceCloneData' example: data: record_type: voice_clone id: 660f9511-f3ac-52e5-b827-557766551111 source_voice_design_id: 550e8400-e29b-41d4-a716-446655440000 source_voice_design_version: 1 name: clone-narrator language: en gender: male label: Speak in a warm, friendly tone created_at: '2024-01-01T00:00:00Z' updated_at: '2024-01-01T00:00:00Z' provider: Telnyx provider_supported_models: - Qwen3TTS provider_voice_id: 660f9511-f3ac-52e5-b827-557766551111 model_id: Qwen3TTS status: active voice-designs_ErrorResponse: type: object description: Standard error response envelope. properties: errors: type: array items: $ref: '#/components/schemas/voice-designs_ErrorObject' example: errors: - code: '10005' title: Resource not found detail: Voice design not found TelnyxQwen3TTSClone: type: object description: Upload-based voice clone using the Telnyx Qwen3TTS model (default). required: - audio_file - name - language - gender - provider properties: audio_file: type: string format: binary description: >- Audio file to clone the voice from. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best quality, provide 5–10 seconds of clear, uninterrupted speech. Maximum size: 5MB. name: type: string maxLength: 255 description: Name for the voice clone. language: type: string pattern: ^([Aa]uto|[a-z]{2,3}(-[A-Za-z0-9]{2,8})*)$ description: ISO 639-1 language code from the Qwen language set. gender: type: string enum: - male - female - neutral description: Gender of the voice clone. ref_text: type: string description: >- Optional transcript of the audio file. Providing this improves clone quality. label: type: string description: Optional custom label describing the voice style. model_id: type: - string - 'null' enum: - Qwen3TTS - null description: TTS model identifier. Nullable/omittable — defaults to Qwen3TTS. provider: type: string enum: - telnyx - Telnyx description: Voice synthesis provider. Must be `telnyx`. TelnyxUltraClone: type: object description: Upload-based voice clone using the Telnyx Ultra model. required: - audio_file - name - language - gender - model_id - provider properties: audio_file: type: string format: binary description: >- Audio file to clone the voice from. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best quality, provide 5–10 seconds of clear, uninterrupted speech. Maximum size: 5MB. name: type: string maxLength: 255 description: Name for the voice clone. language: type: string pattern: ^([Aa]uto|[a-z]{2,3}(-[A-Za-z0-9]{2,8})*)$ description: ISO 639-1 language code from the Ultra language set (40 languages). gender: type: string enum: - male - female - neutral description: Gender of the voice clone. ref_text: type: string description: >- Optional transcript of the audio file. Providing this improves clone quality. label: type: string description: Optional custom label describing the voice style. model_id: type: string enum: - Ultra description: TTS model identifier. Must be `Ultra`. provider: type: string enum: - telnyx - Telnyx description: Voice synthesis provider. Must be `telnyx`. MinimaxClone: type: object description: Upload-based voice clone using the Minimax provider. required: - audio_file - name - language - gender - provider properties: audio_file: type: string format: binary description: >- Audio file to clone the voice from. Supported formats: WAV, MP3, FLAC, OGG, M4A. For best quality, provide 5–10 seconds of clear, uninterrupted speech. Maximum size: 20MB. name: type: string maxLength: 255 description: Name for the voice clone. language: type: string pattern: ^([Aa]uto|[a-z]{2,3}(-[A-Za-z0-9]{2,8})*)$ description: ISO 639-1 language code from the Minimax language set. gender: type: string enum: - male - female - neutral description: Gender of the voice clone. ref_text: type: string description: >- Optional transcript of the audio file. Providing this improves clone quality. label: type: string description: Optional custom label describing the voice style. model_id: type: - string - 'null' enum: - speech-2.8-turbo - null description: TTS model identifier. Nullable — defaults to speech-2.8-turbo. provider: type: string enum: - minimax - Minimax description: Voice synthesis provider. Must be `minimax`. VoiceCloneData: type: object description: A voice clone object. properties: record_type: type: string enum: - voice_clone description: Identifies the resource type. id: type: string format: uuid description: Unique identifier for the voice clone. source_voice_design_id: type: - string - 'null' format: uuid description: UUID of the source voice design. `null` for upload-based clones. source_voice_design_version: type: - integer - 'null' description: >- Version of the source voice design used. `null` for upload-based clones. name: type: string description: Name of the voice clone. language: type: - string - 'null' description: ISO 639-1 language code of the voice clone. gender: type: - string - 'null' enum: - male - female - neutral - null description: Gender of the voice clone. label: type: - string - 'null' description: >- Voice style description. If not explicitly set on upload, falls back to the source design's prompt text. created_at: type: string format: date-time description: Timestamp when the voice clone was created. updated_at: type: string format: date-time description: Timestamp when the voice clone was last updated. provider: type: string enum: - telnyx - minimax - Telnyx - Minimax description: Voice synthesis provider used for this clone. provider_supported_models: type: array items: type: string description: List of TTS model identifiers supported by this clone's provider. provider_voice_id: type: - string - 'null' description: >- Provider-specific voice identifier used for TTS synthesis. May differ from the clone UUID depending on the provider and model. model_id: type: string enum: - Qwen3TTS - Ultra - speech-2.8-turbo description: TTS model identifier for the voice clone. status: type: string enum: - active - pending - failed - expired description: >- Clone status. pending for Ultra clones while on-prem import is in progress, active once ready, failed if verification timed out, expired if not kept alive. voice-designs_ErrorObject: type: object description: A single error object. properties: code: type: string description: Telnyx-specific error code. title: type: string description: Short, human-readable summary of the error. detail: type: string description: Detailed, human-readable explanation of the error. source: type: object description: Reference to the source of the error. properties: pointer: type: string description: A JSON Pointer (RFC 6901) to the field that caused the error. securitySchemes: bearerAuth: scheme: bearer type: http ````