Skip to content

ElevenLabs Eleven v4 Turbo

POST/v1/run

Eleven v4 Turbo is the low-latency tier of ElevenLabs' v4 text-to-speech generation, for real-time and high-volume narration.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to elevenlabs/v4-turbo.

Default: elevenlabs/v4-turbo

stringtextrequired

The text to convert to speech. Supports audio tags such as [whispering] and IPA pronunciation enclosed in forward slashes.

Optional<string>output_format

Output format of the generated audio. Formatted as codec_sample_rate_bitrate.

Allowed values: mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192

Default: mp3_44100_128

Optional<integer>seed

Seed for best-effort reproducibility. Identical output is not guaranteed.

Range: 0 to 4294967295

Optional<number>stability

Voice stability. Lower values allow more expressive delivery; higher values make delivery more consistent.

Range: 0 to 1

Default: 0.5

Optional<number>similarity_boost

How closely the output follows the reference voice. Higher values increase similarity but may reduce naturalness.

Range: 0 to 1

Default: 0.75

Optional<string>apply_text_normalization

Whether to normalize text such as numbers and dates before generation.

Allowed values: auto, on, off

Default: auto

Optional<string>language_code

Language code (ISO 639-1) for speech generation and text normalization.

Optional<boolean>timestamps

Whether to return character-level timing information with the generated audio.

Default: false

Optional<string>voice

The voice to use for speech generation

Default: Rachel

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-speech

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async