Chatterbox Turbo
Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI. We are excited to introduce Chatterbox-Turbo, our most efficient model yet. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with less compute and VRAM than our previous models. We have also distilled the speech-token-to-mel decoder, previously a bottleneck, reducing generation from 10 steps to just one, while retaining high-fidelity audio output. Paralinguistic tags are now native to the Turbo model, allowing you to use [cough], [laugh], [chuckle], and more to add distinct realism. While Turbo was built primarily for low-latency voice agents, it excels at narration and creative workflows. If you like the model but need to scale or tune it for higher accuracy, check out our competitively priced TTS service (link).
- Input price
- $1.00 per 1M chars
- Released
- Dec 2, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced after gateway discounts.
| Provider | Input | Output |
|---|---|---|
DeepInfra deepinfra/ResembleAI/chatterbox-turbo | $1.00/M chars | — |
Pricing
USD on DeepInfra, after gateway discounts.
- Input
- $1.00 per 1M chars
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Response latency
Lower is better0.7sacross providers
Apps
Use Chatterbox Turbo in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Chatterbox Turbo FAQ
Short answers, built from the data on this page.
Chatterbox Turbo is a model from Resemble AI, released on Dec 2, 2025. Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI. We are excited to introduce Chatterbox-Turbo, our most efficient model yet. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with less compute and VRAM than our previous models. We have also distilled the speech-token-to-mel decoder, previously a bottleneck, reducing generation from 10 steps to just one, while retaining high-fidelity audio output. Paralinguistic tags are now native to the Turbo model, allowing you to use [cough], [laugh], [chuckle], and more to add distinct realism. While Turbo was built primarily for low-latency voice agents, it excels at narration and creative workflows. If you like the model but need to scale or tune it for higher accuracy, check out our competitively priced TTS service (link).
On the Respan gateway, input starts at $1.00 per 1M characters on DeepInfra, after gateway discounts.
Chatterbox Turbo is served by DeepInfra.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "chatterbox-turbo". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.