Skip to main content
Watch: I Built an AI App Without Leaving Databricks

ElevenLabs speech APIs - verified

ElevenLabs speech API pricing and models

ElevenLabs: 3 speech-to-text models and 5 text-to-speech models, read from the provider's own pages on October 18, 2026. Its lowest speech-to-text rate converts to $0.22 an hour (Scribe v2). No model here has a scheduled shutdown date.

Read from elevenlabs.io. Compare every speech API

Speech-to-text
3
Text-to-speech
5
Realtime voice
0
Retiring
0

Scribe v2

Speech-to-text - scribe_v2

Price (provider's unit)

$0.22 per hour

“Scribe v2 Speech to Text $0.22 Price per hour”
elevenlabs.io
Converted $/hour (our arithmetic)
  • $0.22stated per hour, no conversion
Languages

90+ languages

“| scribe_v2 | State-of-the-art speech recognition model | 90+ languages |”
elevenlabs.io
Streaming
Not stated
Max audio

3 GB; up to 10 hours (1 hour multichannel)

“- Maximum file size: 3 GB - Maximum duration: 10 hours (standard mode), 1 hour (multichannel mode)”
elevenlabs.io

Note: The FAQ on the same page instead says that in multi-channel mode 'The combined duration of all channels must be less than 10 hours'.

Status
Not stated

Features

  • word-level timestamps, speaker diarization, audio tagging

    “It provides precise word-level timestamps and advanced features like speaker diarization and dynamic audio tagging.”
    elevenlabs.io
  • keyterm prompting add-on

    “Speech to Text $0.22 per hour (Scribe) or $0.39 per hour (Scribe realtime), with keyterm prompting $0.05 per hour and transcript editing $0.07 per hour.”
    elevenlabs.io

Scribe v2 Realtime

Speech-to-text - scribe_v2_realtime

Price (provider's unit)

$0.39 per hour

“Scribe v2 Realtime Speech to Text $0.39 Price per hour”
elevenlabs.io
Converted $/hour (our arithmetic)
  • $0.39stated per hour, no conversion
Languages

90+ languages

“| scribe_v2_realtime | Real-time speech recognition model | 90+ languages |”
elevenlabs.io
Streaming

Yes

“Streaming support: Send audio in chunks while receiving transcripts in real-time”
elevenlabs.io
Max audio
Not stated
Status
Not stated

Features

  • word-level timestamps

    “Precise word-level timestamps”
    elevenlabs.io

~150ms latency.

Scribe v2 Medical

Speech-to-text - scribe_v2_medical

Price (provider's unit)

$0.22 per hour

“Scribe v2 Medical Speech to Text $0.22 Price per hour”
elevenlabs.io
Converted $/hour (our arithmetic)
  • $0.22stated per hour, no conversion
Languages

90+ languages

“| scribe_v2_medical | Speech recognition fine-tuned for clinical audio | 90+ languages |”
elevenlabs.io
Streaming

No

“Scribe v2 Medical is a batch model. For live transcription, use Scribe v2 Realtime.”
elevenlabs.io
Max audio
Not stated
Status
Not stated

Features

  • diarization, timestamps

    “Same request shape as Scribe v2 (keyterms, entity_detection, no_verbatim, diarization, timestamps)”
    elevenlabs.io

HIPAA-eligible: the models page says Business Associate Agreements are available to Enterprise customers, with Zero Retention Mode.

Eleven v4

Text-to-speech - eleven_v4

Current
Price (provider's unit)

$0.08 per 1K characters

“v4 New Text to Speech $0.08 Price per 1K characters”
elevenlabs.io
Languages

90+ languages

“| eleven_v4 | Our most emotionally rich, expressive speech synthesis model | 90+ languages |”
elevenlabs.io
Streaming
Not stated
Limit per request

10,000 characters per request (~10 minutes)

“| eleven_v4 | 10,000 | ~10 minutes |”
elevenlabs.io
Status

new (no preview label)

“v4 New”
elevenlabs.io

Features

  • voice cloning

    “Eleven v4 supports high-fidelity voice cloning with reliable speaker preservation across long text generations.”
    elevenlabs.io
  • audio tags

    “Audio tags for fine-grained control”
    elevenlabs.io

Eleven v4 Turbo

Text-to-speech - eleven_v4_turbo

Current
Price (provider's unit)

$0.04 per 1K characters

“v4 Turbo New Text to Speech $0.04 Price per 1K characters”
elevenlabs.io
Languages

90+ languages

“| eleven_v4_turbo | Our most expressive, real-time speech synthesis model (~100ms†) | 90+ languages |”
elevenlabs.io
Streaming
Not stated
Limit per request
Not stated
Status

new (no preview label)

“v4 Turbo New”
elevenlabs.io

Features

  • voice cloning

    “Eleven v4 Turbo supports high-fidelity voice cloning and delivers results in median inference latency of ~100ms latency.”
    elevenlabs.io

Marketed for real-time and agents (~100ms).

Eleven v3

Text-to-speech - eleven_v3

Legacy
Price (provider's unit)

$0.08 per 1K characters

“v3 Text to Speech $0.08 Price per 1K characters”
elevenlabs.io
Languages

70+ languages

“| eleven_v3 | Human-like and expressive speech generation | 70+ languages |”
elevenlabs.io
Streaming
Not stated
Limit per request

5,000 characters per request (~5 minutes)

“| eleven_v3 | 5,000 | ~5 minutes |”
elevenlabs.io
Status

previous generation

“Eleven v3 is our previous generation speech synthesis model”
elevenlabs.io

Features

  • multi-speaker dialogue

    “Supports multi-speaker dialogue”
    elevenlabs.io

eleven_v3_conversational is priced at $0.04 per 1K characters.

Eleven Multilingual v2

Text-to-speech - eleven_multilingual_v2

Legacy
Price (provider's unit)

$0.08 per 1K characters

“v2 Multilingual Text to Speech $0.08 Price per 1K characters”
elevenlabs.io
Languages

29 languages

“Our multilingual v2 models support 29 languages:”
elevenlabs.io
Streaming
Not stated
Limit per request

10,000 characters per request (~10 minutes)

“| eleven_multilingual_v2 | 10,000 | ~10 minutes |”
elevenlabs.io
Status

previous generation

“Eleven Multilingual v2 is a previous generation emotionally-aware speech synthesis model.”
elevenlabs.io

Eleven Flash v2.5

Text-to-speech - eleven_flash_v2_5

Price (provider's unit)

$0.04 per 1K characters

“Flash / Turbo Text to Speech $0.04 Price per 1K characters”
elevenlabs.io
Languages

32 languages

“32 languages supported”
elevenlabs.io
Streaming
Not stated
Limit per request

40,000 characters per request (~40 minutes)

“| eleven_flash_v2_5 | 40,000 | ~40 minutes |”
elevenlabs.io
Status
Not stated

Docs: 'All eleven_multilingual_v2 languages plus: hu, no, vi'. ~75ms latency.

FAQ

How much does ElevenLabs speech-to-text cost?

Scribe v2: $0.22 per hour. Scribe v2 Realtime: $0.39 per hour. Scribe v2 Medical: $0.22 per hour. Prices are in ElevenLabs's own units as of October 18, 2026.

How much does ElevenLabs text-to-speech cost?

Eleven v4: $0.08 per 1K characters. Eleven v4 Turbo: $0.04 per 1K characters. Eleven v3: $0.08 per 1K characters. Eleven Multilingual v2: $0.08 per 1K characters. Eleven Flash v2.5: $0.04 per 1K characters. Prices are in ElevenLabs's own units as of October 18, 2026.

Sources

Verified from each provider's own pricing pages and model docs; every quote was string-matched against the page that day. Prices are shown in the provider's own unit. Values marked derived were counted by us or taken from Azure's Retail Prices API, not from a pricing page. Prices change without notice; check the linked source before you commit a budget to one.

Newsletter

Know when a speech API changes its prices

One email per week. New model releases, pricing changes and what they mean for what you build.