Buisana ka Bug / Lipotso tsa Likarolo
Ho hloleha ha puisano Motsamaisi oa Lipuisano Moprofesa oa AI Ho kopanngoa ha AI Lipuisano tsa puisano ea AI Motsamaisi oa ho Rekota Sehlooho ho tloha ho _tekong Moetsi oa Litšoantšo tsa Celebrity Ho feta →

AI Voice — Sesame CSM-1B

Ho sebelisoa ka khoebo 380+ li-models Ha ho letšoao la metsi Ha ho hlokahale ho ngolisoa
Mofuta:
+ GPT-5, Claude, Gemini
Mochini oa TTS E bolokiloe ke motho Apache 2.0
Sesame CSM-1B — Sesame CSM-1B — Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio context turn. Self-hosted on Free.ai for the /voice/realtime/ tool.
0 li-characters ~0 tokens
Lipalo tsa theko le palo ea li-character
Ho hlahisa puo...

Ke eng Sesame CSM-1B Na ho utloahala joalo?

Sesame CSM-1B — Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio context turn. Self-hosted on Free.ai for the /voice/realtime/ tool.

Try the box above with: Hello, my name is Sam, and I am reading this sample to demonstrate the voice. — that is the canonical TTS demo phrase.

Ha ho sebelisoa Sesame CSM-1B

Libuka tsa audio

Litlhaku tse telele tse nang le tone e ts'oanang. Ntlafatsa karolo ka nako, kenya e le WAV kapa MP3,'me u e khethe kantle.

Podcast intros

Li-bumper tse khuts'oane tsa ho bula le ho bala li-ad. Ho fetola lebelo bakeng sa matla, ho fetola sebopeho ho MP3 bakeng sa lifaele tse nyane.

IVR + voicemail

Lipotso tsa sistimi ea mohala. Liphetho tsa boleng ba studio ntle le ho ngola, ho ngola, kapa NDAs le talenta ea lentsoe.

Boitlamo

E-ba le li-audio ka lehlakoreng la litaba tse ngotsoeng bakeng sa babali ba nang le mathata a ho bala le ho ngola. E-ba teng ka leqephe leha e le lefe.

Litlhaku tsa mohlala

"Welcome to the show, today we are exploring the future of AI."
"Your package has arrived. Please retrieve it from the front desk."
"Once upon a time, in a quiet village far away, lived a curious child."
"Press one for sales, two for support, or stay on the line for an agent."
"Breaking news: scientists have discovered a new species of deep-sea fish."
"Thank you for choosing us. We appreciate your business and look forward to serving you again."

Litheko

Ho hlophisoa ka GPUs tsa rona. Li-generations li tsoa ho pool ea hau ea mahala ea letsatsi le letsatsi; ha e le hantle, li-packs tsa token li qala ho $ 5 → 200,000 tokens. Ho tloha ho ~ 5 tokens ka sehlooho, ho fihlela ho 100 ka clip.

Mohlala o feletseng oa ho ngola → · Bona li-voices tsohle tsa TTS → · Bapisa li-voices tse 2 ka lehlakoreng le leng →

Likhetho tse tsoetseng pele
Bo_lemo
Tokens e tlase. Get More Tokens
Want better results? Li-models tsa Premium (GPT-5, Claude, Gemini) deliver higher quality. View Plans

❤️ U rata Free.ai? Reka le metsoalle ea hau!

Register ho fumana sehokela sa ho u joetsa le ho fumana li-token tse 25 000 ka motsoalle.

U batla ho feta? Sign up free for 10,000 tokens
Ngola mahala

Ho sebetsana le kopo ea hau...

Sesame CSM-1B — Apache 2.0. Conversational Speech Model designed for low-latency, real-time voice. 24 kHz output, sounds best with a short reference-audio …

Mokhoa oa ho sebelisa AI Voice — Sesame CSM-1B

1
Ke eng eo u e kentseng?

Tlatsa mongolo, kenya faele, kapa hlalosa seo u se batlang. Ha ho hlokahale ak'haonte.

2
Tobetsa ho theha

AI ea rona e sebetsana le kopo ea hau ka metsotsoana ka ho sebelisa li-models tse ntlehali tsa open-source.

3
Tlosa & & arolelana

Kopitsa, kenya kapa arolelana litlamorao tsa hau. Haholo-holo bakeng sa ho sebelisana le batho ba bang le ho rekisa.

Senya sesebelisoa ka API

E-ba le sesebelisoa sena ka ho iketsetsa ho tloha ho kotloloho. OpenAI-compatible REST endpoint, Bearer-token auth, ha ho hlokahale SDK e eketsehileng. Litheko tsa token li lumellana le interface ea webosaeteng.

Litokomane tsa API Fumana konopo ea API 
curl -X POST https://api.free.ai/v1/tts/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from Free.ai", "voice": "af_heart", "model": "kokoro"}'

Li-Tools tsa AI tse Bulehileng tse Bulehileng

Ho hloleha ha puisano
Motsamaisi oa Lipuisano
Moprofesa oa AI
Ho kopanngoa ha AI
Lipuisano tsa puisano ea AI
Motsamaisi oa ho Rekota
Sehlooho ho tloha ho _tekong
Moetsi oa Litšoantšo tsa Celebrity

AI Voice — Sesame CSM-1B — FAQ

Sesame CSM-1B supports a wide range of languages. The exact list depends on the engine; the form on this page accepts any text and the engine will render in its supported languages. See /voice/ for the full multi-engine picker if you need a specific language.

Most engines render neutral-American English by default and a region-appropriate accent for non-English languages. Premium engines may expose accent variants — paste a sample to compare.

SSML support varies by engine. Pause, prosody, and emphasis tags are honored on most premium engines and on a few self-hosted ones. Plain text always works — no markup required.

Streaming TTS is available on premium engines via the /v1/tts/ API endpoint with stream=true. The web UI on this page returns the full clip once rendering finishes.

Sesame CSM-1B runs on our own GPUs. Generation draws from your daily free pool first. Once depleted, paid tokens start at $5 → 200,000 tokens. Roughly ~5 tokens per character, minimum 100 per clip.

Up to 5,000 characters per request on the web UI. For longer pieces (audiobooks, full chapters), use /voice/audiobook/ which chunks and stitches automatically, or call the API in a loop.

Yes — POST a list of strings to /v1/tts/batch/, or use the workspace UI at /workspace/ to chain TTS into a longer pipeline (e.g., translate → speak → stitch).

Yes — POST text to /v1/tts/ with model="Sesame CSM-1B" (or the slug on this page). Returns WAV or MP3. See /api/ for full reference + SDK snippets.

This page is text-to-speech, not voice cloning — the voice is the engine's default. For voice cloning (uploading a reference audio), see /voice/clone/, which requires you to either own the voice rights or have explicit written consent.

Self-hosted engines run on Free.ai-owned GPUs; nothing leaves our servers. Premium engines pass text to upstream model providers under our DPA. We do not train on your inputs and do not sell data.

Yes — Free.ai grants commercial use of generated audio. The engine's underlying license (Apache 2.0, MIT, or vendor terms) is shown above and on the model reference page; in practice this means voiceovers, ads, podcasts, and apps are all in-scope.

Yes — failed jobs auto-refund to the source (daily pool or paid tokens). If a refund does not show up the same day, email contact@free.ai.

Ngolisa mahala bakeng sa 10,000 tokens

E-ba le ak'haonte

Ha ho hlokahale karete ea mokitlane

U tla lekola eng ka sesebelisoa sena?

4.3/5 from 3 ratings

U rata Free.ai? Reka le metsoalle ea hau!