csm-1b

deepinfra/csm-1b

Sesame's CSM-1B (March 2025): a conversational speech model with a Llama backbone and audio decoder producing Mimi codes, able to use prior dialogue audio as context; a base model with no fixed voice, English-focused.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/audio/speech" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/csm-1b",
  "input": "Make every word count.",
  "voice": "auto",
  "response_format": "mp3"
}' --output speech.mp3

Input Price: $5.95 / 1M characters
Output Price: —
Input: Text
Output: Audio

Capabilities

Explore what csm-1b supports, then use the API section for a request tailored to this model.

Batch

Model Information

Provider: DeepInfra
Product: Text-to-Speech
Release Date: Mar 13, 2025
Data Policy: Not specified
Region: US
Input: Text
Output: Audio

Provider Documentation

Playground

Try csm-1b by DeepInfra. Requests use the selected workspace’s credits and API pricing.

csm-1b

Providers

Compare available endpoints, pricing, and context limits for csm-1b.

Provider	Context	Output	Input Price	Output Price	Endpoint
DeepInfra	Not specified	Audio	$5.95 / 1M characters	—	`deepinfra/csm-1b: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	200
Formats	mp3, opus, flac, wav, pcm

Performance

Uptime100%

Time to First AudioMedianP903.16 s

Throughput—

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

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": "deepinfra/csm-1b",
  "input": "Make every word count.",
  "voice": "auto",
  "response_format": "mp3"
}' --output speech.mp3

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`deepinfra/csm-1b` — Required model identifier.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max chars	200
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 TurboDeepInfra	Not specified	$0.85 / 1M characters	—
chatterbox-multilingualDeepInfra	Not specified	$0.85 / 1M characters	—

View All Text-to-Speech