Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
Sesame logo

CSM 1B

NEW

by Sesame

Sesame's Conversational Speech Model, tuned for natural dialogue.

CSM 1B produces remarkably lifelike conversational speech with contextual breathing and pacing, at one of the lowest per-character prices in the catalog. Serves through OpenRouter's speech API.

More details

CSM 1B by Sesame is a fast-speed AI text-to-speech model. CSM 1B produces remarkably lifelike conversational speech with contextual breathing and pacing, at one of the lowest per-character prices in the catalog. Serves through OpenRouter's speech API. Key capabilities include 274 voices across 12 languages, up to 4,096 characters per request.

CSM 1B is priced at $0.008 per 1,000 characters of input text. You can generate speech with CSM 1B on idapt.app alongside 200+ AI models in one workspace.

Voices

6 · 1 languages

Any of these voices can be paired with CSM 1B. Pick a model for quality and speed, a voice for character and language.

Conversational A

English · Female

Conversational B

English · Male

Read Speech A

English · Neutral

Read Speech B

English · Neutral

Read Speech C

English · Neutral

Read Speech D

English · Neutral

Pricing

Cost per 1,000 characters

$0.008

Typical paragraph (~500 chars)

$0.004

Billed on input text length

Capabilities

Speed

Fast: Low-latency, real-time ready

Emotion Control

Natural delivery only

Max Input

4,096 characters per request

Voices

6 voices · 1 languages

Generate speech with CSM 1BView Details

Compare CSM 1B with

OpenAI logo
GPT-4o Mini TTSOpenAI
xAI logo
Grok Voice TTSxAI
Google AI Studio logo
Gemini 3.1 Flash TTS PreviewGoogle AI Studio
MiniMax logo
Speech 2.8 HDMiniMax
MiniMax logo
Speech 2.8 TurboMiniMax
MiniMax logo
Speech 02 HDMiniMax

Frequently Asked Questions

Who created CSM 1B?
CSM 1B was created by Sesame.
How much does CSM 1B cost?
CSM 1B costs $0.008 per 1,000 characters of input text. A short paragraph of roughly 500 characters costs about $0.004.
How fast is CSM 1B?
CSM 1B is classified as a "fast" speed model. It is tuned for low-latency synthesis, making it well suited to interactive and real-time use.
What voices and languages does CSM 1B support?
CSM 1B supports 274 curated voices spanning 12 languages, including English, Chinese, Korean, Japanese, Spanish, and Portuguese. Every voice in the catalog can be used with this model.
Does CSM 1B support emotion control?
CSM 1B does not expose explicit emotion control. Delivery follows the natural intonation of the selected voice.
How much text can CSM 1B synthesize at once?
CSM 1B accepts up to 4,096 characters of input text per request. Longer documents are split automatically across multiple requests.
How does CSM 1B compare to other TTS models?
CSM 1B is one of several text-to-speech models available on idapt. Compare it with GPT-4o Mini TTS, Grok Voice TTS, Gemini 3.1 Flash TTS Preview and more on the audio models directory.
Where can I use CSM 1B?
You can generate speech with CSM 1B on idapt.app — in chat via the media tools, in hands-free voice mode, or through the public API. No separate API key required: idapt provides CSM 1B alongside 200+ AI models in one professional workspace.
Generate speech with CSM 1B
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Demos
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)