--- title: Eleven v3 | Runware Docs url: https://runware.ai/docs/models/elevenlabs-v3 description: Expressive multilingual AI text to speech for studios --- # Eleven v3 Eleven v3 is a premium text to speech model for production audio. It supports 70+ languages with studio grade quality and precise expressive control using inline audio tags. Ideal for narration, podcasts, dialogue, audiobooks, and game voiceover where stable prosody matters. - **ID**: `elevenlabs:27@1` - **Status**: live - **Creator**: ElevenLabs - **Release Date**: June 8, 2025 - **Capabilities**: Text to Audio ## Request Parameters **API Options** Platform-level options for task execution and delivery. ### [taskType](https://runware.ai/docs/models/elevenlabs-v3#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `audioInference` Identifier for the type of task being performed ### [taskUUID](https://runware.ai/docs/models/elevenlabs-v3#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/elevenlabs-v3#request-outputtype) - **Type**: `string` - **Default**: `URL` Audio output type. **Allowed values**: `URL` `base64Data` `dataURI` ### [outputFormat](https://runware.ai/docs/models/elevenlabs-v3#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/elevenlabs-v3#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/elevenlabs-v3#request-audiosettings-bitrate) - **Path**: `audioSettings.bitrate` - **Type**: `integer` - **Min**: `8` Audio bitrate in kbps. #### [channels](https://runware.ai/docs/models/elevenlabs-v3#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/elevenlabs-v3#request-audiosettings-samplerate) - **Path**: `audioSettings.sampleRate` - **Type**: `integer` Audio sample rate in Hz. ### [webhookURL](https://runware.ai/docs/models/elevenlabs-v3#request-webhookurl) - **Type**: `string` - **Format**: `URI` 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. **Learn more** (1 resource): - [Webhooks](https://runware.ai/docs/platform/webhooks) (platform) ### [deliveryMethod](https://runware.ai/docs/models/elevenlabs-v3#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/platform/task-polling) (platform) ### [uploadEndpoint](https://runware.ai/docs/models/elevenlabs-v3#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/elevenlabs-v3#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/elevenlabs-v3#request-includecost) - **Type**: `boolean` - **Default**: `false` Include task cost in the response. ### [numberResults](https://runware.ai/docs/models/elevenlabs-v3#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. **Generation Parameters** Core parameters for controlling the generated content. ### [model](https://runware.ai/docs/models/elevenlabs-v3#request-model) - **Type**: `string` - **Required**: true - **Value**: `elevenlabs:27@1` Identifier of the model to use for generation. **Learn more** (3 resources): - [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide) - [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide) - [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide) ### [seed](https://runware.ai/docs/models/elevenlabs-v3#request-seed) - **Type**: `integer` - **Min**: `0` - **Max**: `4294967295` Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. ### [speech](https://runware.ai/docs/models/elevenlabs-v3#request-speech) - **Path**: `speech.text` - **Type**: `object (2 properties)` - **Required**: true Settings for speech generation. #### [text](https://runware.ai/docs/models/elevenlabs-v3#request-speech-text) - **Path**: `speech.text` - **Type**: `string` - **Max**: `3000` Text to convert to speech. #### [language](https://runware.ai/docs/models/elevenlabs-v3#request-speech-language) - **Path**: `speech.language` - **Type**: `string` - **Min**: `1` Language code for speech generation. **Allowed values**: `af` `ar` `hy` `as` `az` `be` `bn` `bs` `bg` `ca` `ceb` `ny` `hr` `cs` `da` `nl` `en` `et` `fil` `fi` `fr` `gl` `ka` `de` `el` `gu` `ha` `he` `hi` `hu` `is` `id` `ga` `it` `ja` `jv` `kn` `kk` `ky` `ko` `lv` `ln` `lt` `lb` `mk` `ms` `ml` `zh` `mr` `ne` `no` `ps` `fa` `pl` `pt` `pa` `ro` `ru` `sr` `sd` `sk` `sl` `so` `es` `sw` `sv` `ta` `te` `th` `tr` `uk` `ur` `vi` `cy` **Provider Settings** Parameters specific to this model provider. These must be nested inside the \`providerSettings.elevenlabs\` object. ### [textToSpeech](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech) - **Path**: `providerSettings.elevenlabs.textToSpeech` - **Type**: `object (9 properties)` Provider-specific settings for ElevenLabs text-to-speech generation. #### [voiceSettings](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-voicesettings) - **Path**: `providerSettings.elevenlabs.textToSpeech.voiceSettings` - **Type**: `object (4 properties)` Voice settings overriding stored settings for the given voice. Applied only on the given request. ##### [stability](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-voicesettings-stability) - **Path**: `providerSettings.elevenlabs.textToSpeech.voiceSettings.stability` - **Type**: `float` - **Min**: `0` - **Max**: `1` Controls voice stability and randomness between each generation. Lower values introduce broader emotional range, higher values produce a more consistent tone. ##### [useSpeakerBoost](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-voicesettings-usespeakerboost) - **Path**: `providerSettings.elevenlabs.textToSpeech.voiceSettings.useSpeakerBoost` - **Type**: `boolean` Boosts similarity to the original speaker at a slight increase in computational load and latency. ##### [similarityBoost](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-voicesettings-similarityboost) - **Path**: `providerSettings.elevenlabs.textToSpeech.voiceSettings.similarityBoost` - **Type**: `float` - **Min**: `0` - **Max**: `1` Controls how closely the AI adheres to the original voice when attempting to replicate it. ##### [style](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-voicesettings-style) - **Path**: `providerSettings.elevenlabs.textToSpeech.voiceSettings.style` - **Type**: `float` - **Min**: `0` - **Max**: `1` Controls style exaggeration of the voice. Higher values amplify the style of the original speaker but may increase latency. #### [previousText](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-previoustext) - **Path**: `providerSettings.elevenlabs.textToSpeech.previousText` - **Type**: `string` - **Max**: `1000` Text that came before the current request. Improves speech continuity when concatenating multiple generations. #### [nextText](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-nexttext) - **Path**: `providerSettings.elevenlabs.textToSpeech.nextText` - **Type**: `string` - **Max**: `1000` Text that comes after the current request. Improves speech continuity when concatenating multiple generations. #### [applyTextNormalization](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-applytextnormalization) - **Path**: `providerSettings.elevenlabs.textToSpeech.applyTextNormalization` - **Type**: `string` - **Default**: `auto` Controls text normalization behavior (e.g., spelling out numbers). **Allowed values**: - `auto` Automatically decides whether to apply text normalization. - `on` Always applies text normalization. - `off` Skips text normalization entirely. #### [applyLanguageTextNormalization](https://runware.ai/docs/models/elevenlabs-v3#request-providersettings-elevenlabs-texttospeech-applylanguagetextnormalization) - **Path**: `providerSettings.elevenlabs.textToSpeech.applyLanguageTextNormalization` - **Type**: `boolean` - **Default**: `false` Enables language-specific text normalization for proper pronunciation. Currently only supported for Japanese. Warning: can significantly increase latency. ## Response Parameters ### [taskType](https://runware.ai/docs/models/elevenlabs-v3#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `audioInference` Type of the task. ### [taskUUID](https://runware.ai/docs/models/elevenlabs-v3#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the task. ### [audioUUID](https://runware.ai/docs/models/elevenlabs-v3#response-audiouuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the output audio. ### [audioURL](https://runware.ai/docs/models/elevenlabs-v3#response-audiourl) - **Type**: `string` - **Format**: `URI` URL of the output audio. ### [audioBase64Data](https://runware.ai/docs/models/elevenlabs-v3#response-audiobase64data) - **Type**: `string` Base64-encoded audio data. ### [audioDataURI](https://runware.ai/docs/models/elevenlabs-v3#response-audiodatauri) - **Type**: `string` - **Format**: `URI` Data URI of the output audio. ### [seed](https://runware.ai/docs/models/elevenlabs-v3#response-seed) - **Type**: `integer` The seed used for generation. If none was provided, shows the randomly generated seed. ### [cost](https://runware.ai/docs/models/elevenlabs-v3#response-cost) - **Type**: `float` Task cost in USD. Present when `includeCost` is set to `true` in the request. ## Examples ### Midnight Railway Delay Bulletin (Text to Audio) [Listen to audio](https://assets.runware.ai/examples/elevenlabs-v3/ca10c2ed-e9dd-40a0-a839-d03073747660.mp3) **Request**: ```json { "taskType": "audioInference", "taskUUID": "f7ad200e-b09a-43dc-bbed-decf971bb056", "model": "elevenlabs:27@1", "seed": 2794, "speech": { "language": "fr", "text": "[calme, professionnel] Mesdames et messieurs, votre attention, s'il vous plaît. [pause] En raison d'un incident technique survenu en amont, le départ du train de nuit à destination de Clermont-Ferrand est retardé d'environ vingt-cinq minutes. [pause] [plus chaleureux] Nous vous invitons à rester à proximité de la voie B et à consulter les écrans d'information pour les mises à jour en temps réel. [pause] [grave, rassurant] Le personnel en uniforme bleu marine peut vous aider pour les correspondances, l'assistance bagages, ou toute question urgente. [pause] [plus doux] Nous vous remercions de votre patience et de votre compréhension. Le prochain message sera diffusé dans cinq minutes." }, "providerSettings": { "elevenlabs": { "textToSpeech": { "voiceSettings": { "stability": 0.42, "similarityBoost": 0.78, "style": 0.71, "useSpeakerBoost": true }, "applyTextNormalization": "on" } } } } ``` **Response**: ```json { "taskType": "audioInference", "taskUUID": "f7ad200e-b09a-43dc-bbed-decf971bb056", "audioUUID": "807f9a63-b210-40fd-ba6c-3ee4fb80455e", "audioURL": "https://am.runware.ai/audio/os/a20d05/ws/5/ai/807f9a63-b210-40fd-ba6c-3ee4fb80455e.mp3", "seed": 2794, "cost": 0.10926 } ``` --- ### Emergency Lighthouse Fog Broadcast (Text to Audio) [Listen to audio](https://assets.runware.ai/examples/elevenlabs-v3/e39d3f13-5fa4-4f3c-912b-3c3577e8f6f8.mp3) **Request**: ```json { "taskType": "audioInference", "taskUUID": "1b73b87a-a7c9-4820-94d2-a0c6641989a2", "model": "elevenlabs:27@1", "seed": 83929, "speech": { "text": "[serious] Atención a todas las embarcaciones en la ensenada de San Telmo. [pause] La niebla se ha cerrado por completo en el canal norte y la visibilidad ha caído por debajo de cincuenta metros. [urgent] Reduzcan la velocidad de inmediato, activen sus señales acústicas y mantengan rumbo de espera fuera de la zona de arrecifes. [pause] El faro principal opera con energía de respaldo; su destello continuará, pero el equipo de puerto informa corrientes cruzadas más fuertes de lo habitual cerca del espigón este. [calm] Si escuchan esta transmisión, confirmen por radio en el canal dieciséis con el nombre de su nave y el número de personas a bordo. [pause] Repetimos: niebla densa, corrientes intensas y acceso restringido al canal norte hasta nuevo aviso.", "language": "es" }, "providerSettings": { "elevenlabs": { "textToSpeech": { "voiceSettings": { "stability": 0.68, "useSpeakerBoost": true, "similarityBoost": 0.8, "style": 0.56 }, "applyTextNormalization": "auto" } } } } ``` **Response**: ```json { "taskType": "audioInference", "taskUUID": "1b73b87a-a7c9-4820-94d2-a0c6641989a2", "audioUUID": "7c1f2e40-6740-4299-8a64-733356a282ab", "audioURL": "https://am.runware.ai/audio/os/a12d13/ws/5/ai/7c1f2e40-6740-4299-8a64-733356a282ab.mp3", "seed": 83929, "cost": 0.13349 } ``` --- ### Subterranean Transit Wake Announcement (Text to Audio) [Listen to audio](https://assets.runware.ai/examples/elevenlabs-v3/ca579f21-c6c8-432a-8c3b-3e24077ffa34.mp3) **Request**: ```json { "taskType": "audioInference", "taskUUID": "876329ef-1b4e-46ac-8296-f03b2884ff70", "model": "elevenlabs:27@1", "seed": 74347, "speech": { "language": "en", "text": "[calm, intimate] Good morning, passengers of the Meridian Deep Line. [pause] If you are hearing this, your carriage has crossed the basalt threshold and entered the oldest tunnel beneath the city. [slightly warmer] On your left, beyond three meters of reinforced stone, an underground river is moving in total darkness toward the western turbines. [pause] Please remain seated while pressure locks cycle. [soft smile] The gentle flicker in the cabin lights is expected; the generators here were installed one hundred and twelve years ago and still prefer their own rhythm. [more focused] In approximately four minutes, we will arrive at Cinder Quay, where transfer doors open to the freight lifts, the night kitchens, and the lower foundry promenade. [pause] Passengers continuing to Ash Garden should stay aboard. [lower, storytelling tone] Local tradition says the tunnel workers once judged the weather above by listening to how the rails sang below. [brief pause] Today, they would have heard a clear, bright note. [reassuring] Thank you for traveling beneath the city with us." }, "providerSettings": { "elevenlabs": { "textToSpeech": { "voiceSettings": { "stability": 0.62, "similarityBoost": 0.78, "style": 0.71, "useSpeakerBoost": true }, "previousText": "The train departed Hollow Steps Station on schedule and completed descent without incident.", "nextText": "Please gather your belongings before disembarking, and mind the narrow platform gap at Cinder Quay.", "applyTextNormalization": "auto" } } } } ``` **Response**: ```json { "taskType": "audioInference", "taskUUID": "876329ef-1b4e-46ac-8296-f03b2884ff70", "audioUUID": "2e0d89a7-541e-4345-8bef-b12f9164afbd", "audioURL": "https://am.runware.ai/audio/os/a12d13/ws/5/ai/2e0d89a7-541e-4345-8bef-b12f9164afbd.mp3", "seed": 74347, "cost": 0.16856 } ``` --- ### Romanian Funicular Weather Bulletin (Text to Audio) [Listen to audio](https://assets.runware.ai/examples/elevenlabs-v3/67dd7ccb-a230-4dc5-9b09-d631618dc10d.mp3) **Request**: ```json { "taskType": "audioInference", "taskUUID": "bd5d908c-b1be-4661-9304-b435dd35c835", "model": "elevenlabs:27@1", "seed": 96720, "speech": { "language": "ro", "text": "[calm] Bună seara, stimați pasageri. [clear] Funicularul către platoul înalt va pleca în șapte minute de la peronul doi. [measured] Vântul de creastă s-a intensificat, iar temperatura a scăzut sub zero. [reassuring] Personalul a verificat cabinele, sistemele de frânare și traseul de urcare. [slight pause] Vă rugăm să păstrați biletele la îndemână și să fixați bine bagajele mici. [gentle] Copiii trebuie să rămână însoțiți pe toată durata călătoriei. [more serious] Din cauza rafalelor, traversarea poate include scurte opriri de siguranță; acestea sunt normale. [warm] La sosire, urmați felinarele albastre către cabana principală și punctul de orientare. [final, composed] Vă mulțumim pentru răbdare și vă dorim o urcare liniștită." }, "providerSettings": { "elevenlabs": { "textToSpeech": { "applyTextNormalization": "auto", "voiceSettings": { "stability": 0.72, "similarityBoost": 0.8, "style": 0.54, "useSpeakerBoost": true } } } } } ``` **Response**: ```json { "taskType": "audioInference", "taskUUID": "bd5d908c-b1be-4661-9304-b435dd35c835", "audioUUID": "fbc4f7ad-3387-4181-85cf-f1221519ee68", "audioURL": "https://am.runware.ai/audio/os/a14d18/ws/5/ai/fbc4f7ad-3387-4181-85cf-f1221519ee68.mp3", "seed": 96720, "cost": 0.12539 } ``` --- ### Kyoto Alleyway Festival Broadcast (Text to Audio) [Listen to audio](https://assets.runware.ai/examples/elevenlabs-v3/077966ca-d08c-4196-9fbc-07884a375891.mp3) **Request**: ```json { "taskType": "audioInference", "taskUUID": "386f5c21-be5d-4a9a-a304-b42d48c2ed5e", "model": "elevenlabs:27@1", "seed": 50223, "speech": { "language": "ja", "text": "[bright, welcoming] 皆さま、本日の夕暮れの提灯祭りへようこそ。石畳の細い路地には、焼きたての団子、炭火の香り、そして遠くから聞こえる太鼓の響きが満ちています。[gentle pause] この先の朱色の門をくぐると、紙飾りの回廊と、金魚の灯りを浮かべた小さな水盤がございます。[slightly hushed, storytelling] まもなく、古い町家の二階から笛の演奏が始まります。足元にお気をつけのうえ、どうぞ立ち止まって、夏の夜の音をお楽しみください。[warmer, smiling] 迷子のお知らせです。藍色の巾着をお持ちの男の子をお探しのご家族は、柳の木のそばの案内所までお越しください。[clear, ceremonial] なお、灯り流しの受付はあと十五分で終了いたします。短冊に願いごとを書かれる方は、お早めにお並びください。" }, "providerSettings": { "elevenlabs": { "textToSpeech": { "voiceSettings": { "stability": 0.42, "similarityBoost": 0.78, "style": 0.7, "useSpeakerBoost": true }, "applyTextNormalization": "auto", "applyLanguageTextNormalization": true } } } } ``` **Response**: ```json { "taskType": "audioInference", "taskUUID": "386f5c21-be5d-4a9a-a304-b42d48c2ed5e", "audioUUID": "65e82218-3831-4653-ad49-382faf5a32bf", "audioURL": "https://am.runware.ai/audio/os/a03d21/ws/5/ai/65e82218-3831-4653-ad49-382faf5a32bf.mp3", "seed": 50223, "cost": 0.14243 } ```