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

Cartesia speech APIs - verified

Cartesia speech API pricing and models

Cartesia: 1 speech-to-text model and 1 text-to-speech model, read from the provider's own pages on October 18, 2026. Its lowest speech-to-text rate converts to $0.39 an hour (Ink 2). No model here has a scheduled shutdown date.

Read from cartesia.ai, docs.cartesia.ai. Compare every speech API

Speech-to-text
1
Text-to-speech
1
Realtime voice
0
Retiring
0

Speech-to-text

Compare every speech-to-text provider

Ink 2

Speech-to-text - ink-2

Current
Price (provider's unit)

3 credits per second of audio; $0.39 per hour on the Scale plan

“Ink speech-to-text: One hour of audio is only $0.39 on the Scale plan. 3 credits equals 1 second of audio.”
cartesia.ai
Converted $/hour (our arithmetic)
  • $0.39 on the Scale planstated per hour, no conversion
Languages

5 languages derived

“| ink-2 | September 17, 2026 | en, fr, hi, ja, es | Stable |”
Context - docs.cartesia.ai

Note: Count of the language codes in the model table (en, fr, hi, ja, es).

Streaming
Not stated
Max audio
Not stated
Status

stable

“| ink-2 | September 17, 2026 | en, fr, hi, ja, es | Stable |”
docs.cartesia.ai

Features

Text-to-speech

Compare every text-to-speech provider

Sonic 3.6

Text-to-speech - sonic-3.6

Current
Price (provider's unit)

1 credit per character (plans: Pro $5/mo for 100K credits; Startup $49/mo for 1.25M credits; Scale $299/mo for 8M credits)

“Sonic text-to-speech: One minute of audio generation requires 750-800 credits. 1 credit equals 1 character.”
cartesia.ai

Note: Plan prices and credit pools are from the plan cards on the same page. Overage: $65 per 1M credits (Pro), $45 (Startup), $38 (Scale).

Languages

44 languages

“Sonic 3.6 (sonic-3.6) is our fastest, most natural text-to-speech model, with native support for 44 languages.”
docs.cartesia.ai
Streaming
Not stated
Limit per request
Not stated
Status

GA (stable snapshot sonic-3.6-2026-08-27)

“Sonic 3.6 is now Generally Available!”
docs.cartesia.ai

Note: The dated snapshot table on the same page lists sonic-3.6-2026-08-27 (release date August 27, 2026) with status Stable.

Features

  • instant voice cloning (Pro plan and up)

    “Instant voice cloning”
    cartesia.ai

  • professional voice cloning (Startup and up)

    “Speech generated with a PVC costs 1 credit per character”
    cartesia.ai

Cartesia prices TTS in plan credits, not a per-character dollar rate.

FAQ

How much does Cartesia speech-to-text cost?

Ink 2: 3 credits per second of audio; $0.39 per hour on the Scale plan. Prices are in Cartesia's own units as of October 18, 2026.

How much does Cartesia text-to-speech cost?

Sonic 3.6: 1 credit per character (plans: Pro $5/mo for 100K credits; Startup $49/mo for 1.25M credits; Scale $299/mo for 8M credits). Prices are in Cartesia'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.