--- title: HeyGen Voice 1.0 | Runware Docs url: https://runware.ai/docs/models/heygen-voice-1-0 description: Text-to-speech with public voices and instant voice cloning from a single recording --- # HeyGen Voice 1.0 ![HeyGen Voice 1.0](https://assets.runware.ai/covers/heygen-voice-1-0.jpg) HeyGen Voice 1.0 is HeyGen's text-to-speech model for spoken audio in 39 languages, with the language detected from the text when none is set. It speaks with a public voice or clones a new one from a single recording, and returns the cloned voice so later requests can reuse it. It suits voiceovers, narration for training and product videos, and localized content. - **Status**: live - **ID**: `heygen:voice@1.0` - Try in Playground - **Creator**: HeyGen - **Release Date**: October 22, 2026 - **Zero Data Retention**: Yes - **Capabilities**: Text to Audio, Audio to Audio, Checkpoint ## Pricing $0.00003 per character · ~13s per request **4 example generations** - [voice-cloning](https://runware.ai/docs/models/heygen-voice-1-0/examples#example-dutch-flower-auction-lot-call): `$0.00304` (~14s) - [text-to-audio](https://runware.ai/docs/models/heygen-voice-1-0/examples#example-polar-seed-vault-pa-announcement): `$0.00715` (~13s) - [voice-cloning](https://runware.ai/docs/models/heygen-voice-1-0/examples#example-perfume-archive-handling-course-narration): `$0.00792` (~22s) - [text-to-audio](https://runware.ai/docs/models/heygen-voice-1-0/examples#example-ballast-water-compliance-explainer-voiceover): `$0.0108` (~7s) times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing) ## Compatibility & Validation Provide exactly one of: `speech.voice`, `inputs.audio`. ## Notes HeyGen Voice 1.0 speaks with a voice chosen in one of two ways, and a request sends exactly one of them: - **Public voice:** Set `speech.voice` to one of HeyGen's public voices. - **Cloned voice:** Send a recording of the speaker in `inputs.audio`. The model clones the voice, speaks `speech.text` with it and returns its ID in `outputs.voiceId`. Send that ID as `speech.voice` in later requests from the same organization to reuse the voice without the recording. ## Request Parameters **API Options** Platform-level options for task execution and delivery. ### [taskType](https://runware.ai/docs/models/heygen-voice-1-0#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `audioInference` Identifier for the type of task being performed. ### [taskUUID](https://runware.ai/docs/models/heygen-voice-1-0#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [outputType](https://runware.ai/docs/models/heygen-voice-1-0#request-outputtype) - **Type**: `string` - **Default**: `URL` Audio output type. **Allowed values**: `URL` `base64Data` `dataURI` ### [outputFormat](https://runware.ai/docs/models/heygen-voice-1-0#request-outputformat) - **Type**: `string` - **Default**: `MP3` Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - \`MP3\`: Compressed audio, smaller file size. - \`WAV\`: Uncompressed, high-quality audio. - \`FLAC\`: Lossless compression. - \`OGG\`: Open-source compressed audio format (Vorbis codec). **Allowed values**: `MP3` `WAV` `FLAC` `OGG` ### [audioSettings](https://runware.ai/docs/models/heygen-voice-1-0#request-audiosettings) - **Path**: `audioSettings.bitrate` - **Type**: `object (3 properties)` 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. The available sample rates and valid bitrate ranges depend on the output format. For `OGG`, bitrate limits also vary by the number of channels. **MP3 bitrate limits**: Bitrate limits for MP3 are the same regardless of mono or stereo. | Sample Rate | Min Bitrate | Max Bitrate | | --- | --- | --- | | 8,000 Hz | 8 kbps | 64 kbps | | 11,025 Hz | 8 kbps | 64 kbps | | 12,000 Hz | 8 kbps | 64 kbps | | 16,000 Hz | 8 kbps | 160 kbps | | 22,050 Hz | 8 kbps | 160 kbps | | 24,000 Hz | 8 kbps | 160 kbps | | 32,000 Hz | 32 kbps | 320 kbps | | 44,100 Hz | 32 kbps | 320 kbps | | 48,000 Hz | 32 kbps | 320 kbps | **OGG bitrate limits — Mono (1 channel)**: | Sample Rate | Min Bitrate | Max Bitrate | | --- | --- | --- | | 8,000 Hz | 8 kbps | 40 kbps | | 12,000 Hz | 16 kbps | 48 kbps | | 16,000 Hz | 16 kbps | 96 kbps | | 24,000 Hz | 16 kbps | 80 kbps | | 48,000 Hz | 32 kbps | 224 kbps | **OGG bitrate limits — Stereo (2 channels)**: | Sample Rate | Min Bitrate | Max Bitrate | | --- | --- | --- | | 8,000 Hz | 16 kbps | 80 kbps | | 12,000 Hz | 16 kbps | 96 kbps | | 16,000 Hz | 24 kbps | 192 kbps | | 24,000 Hz | 32 kbps | 160 kbps | | 48,000 Hz | 48 kbps | 256 kbps | > [!NOTE] > **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. #### [bitrate](https://runware.ai/docs/models/heygen-voice-1-0#request-audiosettings-bitrate) - **Path**: `audioSettings.bitrate` - **Type**: `integer` - **Min**: `8` Audio bitrate in kbps. #### [channels](https://runware.ai/docs/models/heygen-voice-1-0#request-audiosettings-channels) - **Path**: `audioSettings.channels` - **Type**: `integer` - **Default**: `2` Number of audio channels. 1 for mono, 2 for stereo. **Allowed values**: `1` `2` #### [sampleRate](https://runware.ai/docs/models/heygen-voice-1-0#request-audiosettings-samplerate) - **Path**: `audioSettings.sampleRate` - **Type**: `integer` Audio sample rate in Hz. ### [webhookURL](https://runware.ai/docs/models/heygen-voice-1-0#request-webhookurl) - **Type**: `string` - **Format**: `uri` Webhook URL that receives JSON responses 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. **Learn more** (1 resource): - [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform) ### [deliveryMethod](https://runware.ai/docs/models/heygen-voice-1-0#request-deliverymethod) - **Type**: `string` - **Default**: `sync` Determines how the API delivers task results. **Allowed values**: - `sync` Returns complete results directly in the API response. - `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. **Learn more** (1 resource): - [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform) ### [uploadEndpoint](https://runware.ai/docs/models/heygen-voice-1-0#request-uploadendpoint) - **Type**: `string` - **Format**: `uri` 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. **Common use cases:** - **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs. - **CDN integration**: Upload to content delivery networks for immediate distribution. ```text // S3 presigned URL for secure upload https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600 // Google Cloud Storage presigned URL https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789 // Custom storage endpoint https://storage.example.com/uploads/generated-image.jpg ``` The content data will be sent as the request body to the specified URL when generation is complete. ### [ttl](https://runware.ai/docs/models/heygen-voice-1-0#request-ttl) - **Type**: `integer` - **Min**: `60` Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. ### [includeCost](https://runware.ai/docs/models/heygen-voice-1-0#request-includecost) - **Type**: `boolean` Include task cost in the response. ### [numberResults](https://runware.ai/docs/models/heygen-voice-1-0#request-numberresults) - **Type**: `integer` - **Min**: `1` - **Max**: `4` - **Default**: `1` Number of results to generate. Each result uses a different seed, producing variations of the same parameters. ### [routing](https://runware.ai/docs/models/heygen-voice-1-0#request-routing) - **Path**: `routing.preferences` - **Type**: `object (6 properties)` Model router options. Only read when `model` is `auto`, and never sent to the model. #### [preferences](https://runware.ai/docs/models/heygen-voice-1-0#request-routing-preferences) - **Path**: `routing.preferences` - **Type**: `object (3 properties)` Relative importance of each dimension when models are compared. Weights, not thresholds. ##### [quality](https://runware.ai/docs/models/heygen-voice-1-0#request-routing-preferences-quality) - **Path**: `routing.preferences.quality` - **Type**: `integer` - **Min**: `0` - **Max**: `5` Importance of one dimension. `0` leaves it out of the decision. ##### [speed](https://runware.ai/docs/models/heygen-voice-1-0#request-routing-preferences-speed) - **Path**: `routing.preferences.speed` - **Type**: `integer` - **Min**: `0` - **Max**: `5` Importance of one dimension. `0` leaves it out of the decision. ##### [cost](https://runware.ai/docs/models/heygen-voice-1-0#request-routing-preferences-cost) - **Path**: `routing.preferences.cost` - **Type**: `integer` - **Min**: `0` - **Max**: `5` Importance of one dimension. `0` leaves it out of the decision. #### [maxPrice](https://runware.ai/docs/models/heygen-voice-1-0#request-routing-maxprice) - **Path**: `routing.maxPrice` - **Type**: `float` - **Min**: `0` Upper bound on what this request may cost, in USD. A model whose cost cannot be bounded is not chosen. #### [requirements](https://runware.ai/docs/models/heygen-voice-1-0#request-routing-requirements) - **Path**: `routing.requirements` - **Type**: `string` - **Max**: `3000` Conditions the result has to meet, in plain words, such as a style or a feature. A model that cannot meet them is not chosen. Output size is set with width and height rather than described here. **Inputs** Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object. ### [audio](https://runware.ai/docs/models/heygen-voice-1-0#request-inputs-audio) - **Path**: `inputs.audio` - **Type**: `string` - **File size**: `up to 100 MB` Audio input (UUID or URL). Recording to clone the voice from. Only the first 3 minutes are used. **Core Parameters** Primary parameters that define the task output. ### [model](https://runware.ai/docs/models/heygen-voice-1-0#request-model) - **Type**: `string` - **Required**: true - **Value**: `heygen:voice@1.0` Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router). **Learn more** (3 resources): - [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn) - [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn) - [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn) ### [speech](https://runware.ai/docs/models/heygen-voice-1-0#request-speech) - **Path**: `speech.text` - **Type**: `object (3 properties)` - **Required**: true Settings for speech generation. #### [text](https://runware.ai/docs/models/heygen-voice-1-0#request-speech-text) - **Path**: `speech.text` - **Type**: `string` - **Required**: true - **Min**: `1` - **Max**: `5000` Text to convert to speech. Plain text only, so SSML and `` tags are not supported. #### [voice](https://runware.ai/docs/models/heygen-voice-1-0#request-speech-voice) - **Path**: `speech.voice` - **Type**: `string` Voice identifier to use for speech generation. A public HeyGen voice, or the `outputs.voiceId` of an earlier `inputs.audio` request from the same organization. **Allowed values**: - `fca00394b42949c2a939acd456e3291f` Bram, calm and gentle. - `41f17b4ebd334ac99a91c2aada5f86d7` Cecily, warm and friendly. - `69a83c97b51a4bb5a3d0fb0ce1699431` Corinne, bright and energetic. - `3195f3da04c94984a0a77a4b757c8119` Elowen, warm and soothing. - `5f9c155f4108437f970c308c95b06e11` Ewan, bright and energetic. - `6ab7f456be114a109f8c8006567f638c` Felicity, upbeat and lively. - `826be797681d4b1a92042b54b3c75c64` Gareth, conversational and easygoing. - `9b71011176ac49ee8d0936c36566d665` Hugh, firm and measured. - `660022d4c7ff428cbb5787685e8df571` Iona, bright and energetic. - `f415c3cd23db47c1b4fe834387d26449` Jocelyn, bright and energetic. - `7e48c8d406b04a8089c5eb3cd057cb2e` Jonah, clear and professional. - `d322a996ccc54505a170d5f9db7fd7dd` Kieran, warm and friendly. - `049413e41c334753984c294d694afb5c` Lucian, conversational and easygoing. - `880609d7e76e4360ba44e65f0774d4e6` Marielle, upbeat and lively. - `aa9746e325ff46d482a54fe5bc87890f` Meredith, serious and composed. - `83548de556df48ba8c09c42a57c51d85` Nadine, calm and gentle. - `48476d5a314943149b9522fb666b128a` Noelle, warm and soothing. - `7bb4df56d7714d33bb88ed1dde8128f6` Rory, upbeat and lively. - `75300849b571414c8d62693289cb6509` Sabrina, upbeat and lively. - `8be9884ebd16499fbe0efb274e769ed5` Simon, calm and gentle. - `95fae2bb58b647c58ea32e6667f86b0e` Soren, firm and measured. - `a6752292cd204ac4a80a25fb575b1327` Tabitha, conversational and easygoing. - `f43e55ae9fb540c6b62e23081c951748` Vincent, thoughtful and clear. - `742d54da82fb46a8be11480d9ec6e3c3` Weston, warm and friendly. #### [language](https://runware.ai/docs/models/heygen-voice-1-0#request-speech-language) - **Path**: `speech.language` - **Type**: `string` - **Min**: `1` Language code for speech generation. Detected from `speech.text` when omitted. **Allowed values**: `ar` `be` `bg` `ca` `cs` `da` `de` `el` `en` `es` `fa` `fi` `fr` `he` `hi` `hr` `hu` `id` `it` `ja` `ko` `mk` `ms` `nl` `pl` `pt` `ro` `ru` `sk` `sl` `sr` `sv` `ta` `th` `tl` `tr` `uk` `vi` `zh` **Settings** Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object. ### [expressiveness](https://runware.ai/docs/models/heygen-voice-1-0#request-settings-expressiveness) - **Path**: `settings.expressiveness` - **Type**: `float` - **Min**: `0` - **Max**: `1` - **Step**: `0.01` - **Default**: `1` Expressiveness of the delivery. ## Response Parameters ### [taskType](https://runware.ai/docs/models/heygen-voice-1-0#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `audioInference` Identifier for the type of task this response belongs to. ### [taskUUID](https://runware.ai/docs/models/heygen-voice-1-0#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [audioUUID](https://runware.ai/docs/models/heygen-voice-1-0#response-audiouuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the output audio. ### [audioURL](https://runware.ai/docs/models/heygen-voice-1-0#response-audiourl) - **Type**: `string` - **Format**: `uri` URL of the output audio. ### [audioBase64Data](https://runware.ai/docs/models/heygen-voice-1-0#response-audiobase64data) - **Type**: `string` Base64-encoded audio data. ### [audioDataURI](https://runware.ai/docs/models/heygen-voice-1-0#response-audiodatauri) - **Type**: `string` - **Format**: `uri` Data URI of the output audio. ### [seed](https://runware.ai/docs/models/heygen-voice-1-0#response-seed) - **Type**: `integer` The seed used for generation. If none was provided, shows the randomly generated seed. ### [cost](https://runware.ai/docs/models/heygen-voice-1-0#response-cost) - **Type**: `float` Task cost in USD. Present when `includeCost` is set to `true` in the request. ### [outputs](https://runware.ai/docs/models/heygen-voice-1-0#response-outputs) - **Path**: `outputs.voiceId` - **Type**: `object (1 property)` Generated output artifacts. #### [voiceId](https://runware.ai/docs/models/heygen-voice-1-0#response-outputs-voiceid) - **Path**: `outputs.voiceId` - **Type**: `string` ID of the voice cloned from `inputs.audio`, returned only when `inputs.audio` is sent. Pass it as `speech.voice` in later requests from the same organization. ## Examples ### text-to-audio (text-to-audio) [Listen to audio](https://assets.runware.ai/examples/heygen-voice-1-0/83974f44-b95a-4e41-9c4b-531aca9c0e63.mp3) > **Prompt**: Attention, conservation team. Chamber three has reached stable temperature, and the evening inventory may now begin. Please keep the inner doors closed while seed cases are in transit. The next surface transfer is scheduled after the weather station gives clearance. Until then, return all scanning equipment to the decontamination bay and report any damaged seals to cold-storage control. Night staff, your briefing will begin in the lower archive at twenty-one hundred hours. ```json { "taskType": "audioInference", "taskUUID": "c09c8094-99b0-43a8-9ac6-56018544b3d8", "model": "heygen:voice@1.0", "speech": { "text": "Attention, conservation team. Chamber three has reached stable temperature, and the evening inventory may now begin. Please keep the inner doors closed while seed cases are in transit. The next surface transfer is scheduled after the weather station gives clearance. Until then, return all scanning equipment to the decontamination bay and report any damaged seals to cold-storage control. Night staff, your briefing will begin in the lower archive at twenty-one hundred hours.", "voice": "aa9746e325ff46d482a54fe5bc87890f" } } ``` --- ### text-to-audio (text-to-audio) [Listen to audio](https://assets.runware.ai/examples/heygen-voice-1-0/901882ea-9882-429e-90a6-28ec2c53d2df.mp3) > **Prompt**: Every voyage moves more than cargo. Ballast water can carry microscopic organisms between ecosystems, threatening local fisheries and exposing operators to costly compliance failures. Before discharge, confirm that the vessel’s treatment system is operational, verify the approved flow rate, and check ultraviolet intensity, filter pressure, and alarm status. Record each operation accurately in the ballast water record book, including the date, location, volume, and treatment method. If the system reports a fault, stop the discharge and follow the vessel’s contingency plan. Effective ballast water management protects marine habitats, keeps inspections straightforward, and helps every voyage arrive responsibly. ```json { "taskType": "audioInference", "taskUUID": "430bee4f-7075-49fa-bfbf-5718f958f3f4", "model": "heygen:voice@1.0", "speech": { "text": "Every voyage moves more than cargo. Ballast water can carry microscopic organisms between ecosystems, threatening local fisheries and exposing operators to costly compliance failures. Before discharge, confirm that the vessel’s treatment system is operational, verify the approved flow rate, and check ultraviolet intensity, filter pressure, and alarm status. Record each operation accurately in the ballast water record book, including the date, location, volume, and treatment method. If the system reports a fault, stop the discharge and follow the vessel’s contingency plan. Effective ballast water management protects marine habitats, keeps inspections straightforward, and helps every voyage arrive responsibly.", "voice": "7e48c8d406b04a8089c5eb3cd057cb2e" } } ``` --- ### voice-cloning (voice-cloning) [Listen to audio](https://assets.runware.ai/examples/heygen-voice-1-0/10dabe99-aa1a-4d8d-b467-40274db8b358.mp3) > **Prompt**: Begin with the bottle resting upright in its padded tray. Without touching the stopper, inspect the neck for crystalline residue, hairline fractures, or signs of evaporation. Next, check the label under soft, indirect light. If the paper is lifting, stained, or brittle, do not attempt to flatten it. Record the condition from several angles, then return the bottle to its assigned compartment. Even when the fragrance has faded, the vessel, label, and remaining sediment can reveal how the perfume was made, marketed, and used. ```json { "taskType": "audioInference", "taskUUID": "3303418e-f5a9-4767-9997-43e0b50a4101", "model": "heygen:voice@1.0", "speech": { "text": "Begin with the bottle resting upright in its padded tray. Without touching the stopper, inspect the neck for crystalline residue, hairline fractures, or signs of evaporation. Next, check the label under soft, indirect light. If the paper is lifting, stained, or brittle, do not attempt to flatten it. Record the condition from several angles, then return the bottle to its assigned compartment. Even when the fragrance has faded, the vessel, label, and remaining sediment can reveal how the perfume was made, marketed, and used.", "language": "en" }, "inputs": { "audio": "https://assets.runware.ai/assets/inputs/76db71b5-5b90-4dc7-a45e-f0c6b03512ae.mp3" } } ``` --- ### voice-cloning (voice-cloning) [Listen to audio](https://assets.runware.ai/examples/heygen-voice-1-0/d754ba9a-15ed-4fc5-8f22-71456d8236c9.mp3) > **Prompt**: Kavel zevenendertig: honderdtwintig bossen witte tulpen, kwaliteit A1, rechtstreeks uit Rijnsburg. De klok loopt. Negentig cent, vijfentachtig, tachtig, vijfenzeventig. Verkocht aan koper tweehonderdzes. ```json { "taskType": "audioInference", "taskUUID": "93d0f3f1-d052-45ea-a822-b7e452f3e9e0", "model": "heygen:voice@1.0", "speech": { "text": "Kavel zevenendertig: honderdtwintig bossen witte tulpen, kwaliteit A1, rechtstreeks uit Rijnsburg. De klok loopt. Negentig cent, vijfentachtig, tachtig, vijfenzeventig. Verkocht aan koper tweehonderdzes.", "language": "nl" }, "inputs": { "audio": "https://assets.runware.ai/assets/inputs/6c12314a-0bd3-4fd5-9fd4-7e5375b923a3.mp3" } } ```