MODEL ID elevenlabs:24@1

live

Eleven Flash v2.5

by ElevenLabs December 19, 2024

Eleven Flash v2.5 is a real time text to speech model for voice agents and interactive apps. It delivers natural speech in about 75 ms latency across 32 languages. Use it for low latency conversational AI, games, live tools, and large scale TTS workloads.

API Options

Platform-level options for task execution and delivery.

taskType string required value: audioInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Audio output type.

Allowed values 3 values

outputFormat 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 4 values

audioSettings object

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

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.

Properties 3 properties

audioSettings » bitrate bitrate integer min: 8: Audio bitrate in kbps.

audioSettings » channels channels integer default: 2: Number of audio channels. 1 for mono, 2 for stereo.

Allowed values 2 values

audioSettings » sampleRate sampleRate integer: Audio sample rate in Hz.

webhookURL string 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
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string 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.

// 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 integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults 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 string required value: elevenlabs:24@1

Identifier of the model to use for generation.

Learn more 3 resources

seed 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 object required

Settings for speech generation.

Properties 2 properties

speech » text text string max: 40000: Text to convert to speech.

speech » language language string min: 1: Language code for speech generation.

Allowed values 32 values

Provider Settings

Parameters specific to this model provider. These must be nested inside the providerSettings.elevenlabs object.

providerSettings » elevenlabs » textToSpeech textToSpeech object

Provider-specific settings for ElevenLabs text-to-speech generation.

Properties 5 properties

providerSettings » elevenlabs » textToSpeech » voiceSettings voiceSettings object

Voice settings overriding stored settings for the given voice. Applied only on the given request.

Properties 4 properties

providerSettings » elevenlabs » textToSpeech » voiceSettings » stability stability 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.

providerSettings » elevenlabs » textToSpeech » voiceSettings » useSpeakerBoost useSpeakerBoost boolean: Boosts similarity to the original speaker at a slight increase in computational load and latency.

providerSettings » elevenlabs » textToSpeech » voiceSettings » similarityBoost similarityBoost float min: 0 max: 1: Controls how closely the AI adheres to the original voice when attempting to replicate it.

providerSettings » elevenlabs » textToSpeech » voiceSettings » style style float min: 0 max: 1: Controls style exaggeration of the voice. Higher values amplify the style of the original speaker but may increase latency.

providerSettings » elevenlabs » textToSpeech » previousText previousText string max: 1000: Text that came before the current request. Improves speech continuity when concatenating multiple generations.

providerSettings » elevenlabs » textToSpeech » nextText nextText string max: 1000: Text that comes after the current request. Improves speech continuity when concatenating multiple generations.

providerSettings » elevenlabs » textToSpeech » applyTextNormalization applyTextNormalization string default: auto

Controls text normalization behavior (e.g., spelling out numbers).

Allowed values 3 values

: Automatically decides whether to apply text normalization.
: Always applies text normalization.
: Skips text normalization entirely.

providerSettings » elevenlabs » textToSpeech » applyLanguageTextNormalization applyLanguageTextNormalization boolean default: false: Enables language-specific text normalization for proper pronunciation. Currently only supported for Japanese. Warning: can significantly increase latency.

taskType string required value: audioInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

audioUUID string required UUID v4: UUID of the output audio.

audioURL string URI: URL of the output audio.

audioBase64Data string: Base64-encoded audio data.

audioDataURI string URI: Data URI of the output audio.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Audio

Antique Planetarium Welcome Address

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "8b925346-7add-40c7-a184-bc91ec4a95cb",
  "model": "elevenlabs:24@1",
  "seed": 82622,
  "speech": {
    "language": "en",
    "text": "Good evening, travelers. In a few moments, the dome above you will dim, and the first stars of tonight's program will appear. Please settle into your seats and let your eyes adjust to the dark. We will begin close to home, tracing the familiar line of the winter constellations, then drift outward beyond the bright edge of our neighborhood into regions where distance is measured in centuries of light. If you are joining us for the first time, you do not need to know any names. Simply look up, follow the guiding beam, and listen. By the end of our journey, the sky may feel a little larger, and Earth a little more precious."
  },
  "providerSettings": {
    "elevenlabs": {
      "textToSpeech": {
        "applyTextNormalization": "auto",
        "voiceSettings": {
          "stability": 0.42,
          "similarityBoost": 0.78,
          "style": 0.58,
          "useSpeakerBoost": true
        }
      }
    }
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "8b925346-7add-40c7-a184-bc91ec4a95cb",
  "audioUUID": "641f7e37-d5e9-4f75-b76d-014a17bde046",
  "audioURL": "https://am.runware.ai/audio/os/a12d13/ws/5/ai/641f7e37-d5e9-4f75-b76d-014a17bde046.mp3",
  "seed": 82622,
  "cost": 0.08947
}

Text to Audio

Emergency Tram Intercom Bulletin

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "4f10c705-5472-4315-a757-5c70f22f0a50",
  "model": "elevenlabs:24@1",
  "seed": 43900,
  "speech": {
    "text": "Attention passengers: service on the East Loop is temporarily paused between Harbor Gate and Pine Junction due to a signal fault. Shuttle buses are departing from Bay 3 every 12 minutes. If you are traveling to Riverside Terminal, remain on board for the alternate route announcement in 30 seconds. We apologize for the disruption and thank you for your patience.",
    "language": "en"
  },
  "providerSettings": {
    "elevenlabs": {
      "textToSpeech": {
        "voiceSettings": {
          "stability": 0.72,
          "similarityBoost": 0.78,
          "style": 0.34,
          "useSpeakerBoost": true
        },
        "applyTextNormalization": "on",
        "previousText": "Good afternoon, this is a network update.",
        "nextText": "Please listen for further instructions from station staff."
      }
    }
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "4f10c705-5472-4315-a757-5c70f22f0a50",
  "audioUUID": "57bf6f10-0a1a-4148-8c8a-31dc8710ea5c",
  "audioURL": "https://am.runware.ai/audio/os/a25d05/ws/5/ai/57bf6f10-0a1a-4148-8c8a-31dc8710ea5c.mp3",
  "seed": 43900,
  "cost": 0.05407
}

Text to Audio

Orbital Docking Countdown Brief

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "8b10a718-b30e-468e-afd3-cf69336ad9a4",
  "model": "elevenlabs:24@1",
  "seed": 88075,
  "speech": {
    "text": "Attention inbound crew of the cargo shuttle Peregrine. Docking corridor C-12 is now active. Approach speed should not exceed 0.3 meters per second beyond the outer guide ring. Crosswinds from vent array 4 may cause minor drift on port-side thrusters. Window for final alignment opens in 18 seconds. If your guidance display flickers, maintain heading and await manual tone confirmation. Repeat: maintain heading. Dockmaster Hale authorizing clamp sequence on my count. Three. Two. One. Contact expected now.",
    "language": "en"
  },
  "providerSettings": {
    "elevenlabs": {
      "textToSpeech": {
        "applyTextNormalization": "on",
        "voiceSettings": {
          "stability": 0.42,
          "similarityBoost": 0.78,
          "style": 0.61,
          "useSpeakerBoost": true
        }
      }
    }
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "8b10a718-b30e-468e-afd3-cf69336ad9a4",
  "audioUUID": "d4b213ca-fd39-4446-a7ec-34774eb20619",
  "audioURL": "https://am.runware.ai/audio/os/a23d05/ws/5/ai/d4b213ca-fd39-4446-a7ec-34774eb20619.mp3",
  "seed": 88075,
  "cost": 0.09306
}

Text to Audio

Submersible Black Box Transmission

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "8888535a-2ee9-4af6-99ed-b0376a3eb5ad",
  "model": "elevenlabs:24@1",
  "seed": 65534,
  "speech": {
    "text": "Archive buoy Kappa-seven, this is pilot Mirek Voss transmitting from bathysphere Nacre. If this reaches surface control, note the following in order. Primary floodgate sealed at fourteen minutes past shift change. Port thruster unresponsive after contact with loose cable or vine-like debris. Cabin pressure stable for now. I am reducing power to navigation glass and heating to preserve emergency cells. There is a repeating metallic tapping on the outer hull every eleven seconds. It is too regular to be current or drift. I have marked my position against the canyon wall using the last flare. Please do not send an automated ping burst; the echo in this trench is distorting sonar returns. Send a quiet approach team with a manual line. If Lena is on comms, tell her the charm tied to panel three was right. The old maps were wrong by nearly a full kilometer. End log, and please confirm receipt.",
    "language": "en"
  },
  "providerSettings": {
    "elevenlabs": {
      "textToSpeech": {
        "previousText": "Bathysphere Nacre emergency log begins after impact alarm.",
        "nextText": "Secondary note: oxygen reserve estimate pending manual recalculation.",
        "applyTextNormalization": "auto",
        "voiceSettings": {
          "stability": 0.42,
          "similarityBoost": 0.72,
          "style": 0.58,
          "useSpeakerBoost": true
        }
      }
    }
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "8888535a-2ee9-4af6-99ed-b0376a3eb5ad",
  "audioUUID": "8a21b704-fb41-4e19-9093-4dddbe9f1eb3",
  "audioURL": "https://am.runware.ai/audio/os/a04d20/ws/5/ai/8a21b704-fb41-4e19-9093-4dddbe9f1eb3.mp3",
  "seed": 65534,
  "cost": 0.14426
}