Capabilities
Explore what Chatterbox Turbo supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- DeepInfra
- Product
- Text-to-Speech
- Release Date
- Dec 2025
- Data Policy
- Not specified
- Region
- US
- Input
- Text
- Output
- Audio
Playground
Try Chatterbox Turbo by DeepInfra. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Chatterbox Turbo.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| DeepInfra | Not specified | Audio | $0.85 / 1M characters | — | resemble/chatterbox-turbo:deepinfra |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, flac, wav, pcm |
Provider Notes
Chatterbox Turbo requires the common voice field to contain a custom voice ID created through DeepInfra's voice API; DeepInfra does not supply a default Chatterbox voice, so voice=auto is rejected before dispatch. OpenAI-compatible raw audio is the default. Native JSON preserves DeepInfra metadata and Kokoro word timings; Kokoro also supports native and ElevenLabs-compatible streaming. Chatterbox supports OpenAI-compatible audio, native JSON, and buffered ElevenLabs-compatible requests; DeepInfra publishes no streaming schema for this model, so AudioLab rejects both Chatterbox streaming transports before calling upstream.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "resemble/chatterbox-turbo",
"input": "Make every word count.",
"voice": "YOUR_DEEPINFRA_VOICE_ID",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | resemble/chatterbox-turbo — Required model identifier. |
transport | View Accepted Values |
service_tier | View Accepted Values |
version | View Accepted Values |
language_code | View Accepted Values |
webhook | View Accepted Values |
kokoro | View Accepted Values |
chatterbox | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, flac, wav, pcm |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| audio8DeepInfra | Not specified | $4.25 / 1M characters | — |
| qwen3-ttsDeepInfra | Not specified | $17.00 / 1M characters | — |
| qwen3-tts-voicedesignDeepInfra | Not specified | $17.00 / 1M characters | — |
| higgs-audio-v2.5DeepInfra | Not specified | $17.00 / 1M characters | — |
| chatterbox-multilingualDeepInfra | Not specified | $0.85 / 1M characters | — |
| csm-1bDeepInfra | Not specified | $5.95 / 1M characters | — |