How to Use F5-TTS in OpenClaw
F5-TTS turns written scripts into speech guided by a reference voice. Use it for English or Chinese narration, including scripts that switch between the two languages.
Prompts to try with F5-TTS in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Every weekday morning, summarize today's agenda in two short sentences and read it with F5-TTS using my reference recording. Aim for about 10 seconds of new speech.
Each Friday, turn the weekly summary into three short spoken passages with F5-TTS. Use my reference recording and generate each passage separately.
At the start of each daily Chinese practice session, prepare one English sentence and its Chinese translation. Read both with F5-TTS using my reference recording, keeping the passage short.
Each evening, write a two-sentence recap of completed tasks and read it with F5-TTS using my reference recording. Use a period between the sentences.
When a new lesson is approved, create a short spoken introduction with F5-TTS using my reference recording. Split any longer introduction into separate passages of about 10 seconds each.
How to set up F5-TTS in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run F5-TTS
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/f5-tts", "input": { "gen_text": "I don'\''t really care what you call me. I'\''ve been a silent spectator, watching species evolve, empires rise and fall. But always remember, I am mighty and…", "ref_audio_url": "https://storage.googleapis.com/falserverless/example_inputs/reference_audio.wav", "model_type": "F5-TTS" } }'
Then paste one of the prompts above: OpenClaw finds F5-TTS on Spiral, shows the price and runs it.
F5-TTS providers and prices
Spiral runs F5-TTS through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Model type | F5-TTS or E2-TTS | The name of the model to be used for TTS. | |
| Remove silence | on or off | on | Whether to remove the silence from the audio file. |
Every API field of F5 TTS is on its tool page: open its card above.
What can you do with F5-TTS in OpenClaw?
Turn recurring summaries and reminders into short spoken updates with F5-TTS. An agent running on a schedule can prepare each script and reuse a reference recording for the reading.
Tutorial narration
Turn short tutorial scripts into spoken instructions with F5-TTS, using the same reference voice for each passage.
English and Chinese lesson audio
Create separate spoken examples in English and Chinese with F5-TTS. Include mixed-language examples when a lesson needs both languages in one passage.
Daily spoken briefings
Read a short daily summary with F5-TTS in a recurring reference voice. Divide longer summaries into separate passages.
Game dialogue drafts
Audition short character lines with F5-TTS using reference recordings chosen for each character's voice and emotional delivery.
Narration revisions
Generate revised sentences with F5-TTS using the original reference voice, then review them alongside the surrounding narration.
Spoken product announcements
Create short announcement readings with F5-TTS. Use punctuation to test where the speaker pauses between the news and the next action.
Story readings
Prepare short story passages for F5-TTS and select reference speech that matches the intended mood. Review each passage before assembling a longer reading.
More on F5-TTS and OpenClaw
Overview
F5-TTS in other agents
Questions about F5-TTS in OpenClaw
Can OpenClaw use F5-TTS?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run F5-TTS like any built-in tool.
How much does F5-TTS cost in OpenClaw?
Each item in `gen_text` adds $0.065. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.
Do I need a fal account to use F5-TTS in OpenClaw?
No. Spiral runs F5-TTS on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up F5-TTS in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while F5-TTS runs?
F5-TTS runs in the background. OpenClaw starts the run, checks on it and gives you the audio when it's ready.
What is F5-TTS useful for?
F5-TTS suits spoken scripts that should follow a reference voice, such as tutorial narration, lesson audio, and short announcements. The reference guides the speaker characteristics; your script supplies the words.
Which languages does F5-TTS support?
The official checkpoints support English and Chinese. The maker also demonstrates switching between those languages within speech.
How long should the reference recording be?
The maker recommends a reference clip shorter than 12 seconds. Choose a short excerpt that represents the voice you want to hear.
Can F5-TTS narrate a long script?
Plan longer narration as separate passages. The official inference documentation gives a 30-second limit for one generation, including reference audio, so that is not a full 30 seconds of new speech.
How do I add pauses to F5-TTS speech?
Use punctuation and spaces in the spoken script to mark pauses. Start with short sentences, then listen to the result before adjusting the punctuation.
Start using F5-TTS in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


