How to Use Seed Speech TTS 2.0 in Claude Code
Seed Speech TTS 2.0 turns written scripts into expressive narration for explainers, assistant replies, and support messages. Compared with Seed Speech TTS 1.0, it adds natural-language direction for delivery.
Prompts to try with Seed Speech TTS 2.0 in Claude Code
Copy an example into Claude Code, or ask in your own words.
Read the onboarding documentation in this project and draft a 90-word spoken introduction. Use Seed Speech TTS 2.0 to narrate it with a patient, conversational delivery, and save the script beside the audio.
Find the password-reset instructions in this project's interface copy. Create a short narration with Seed Speech TTS 2.0, using a calm, reassuring delivery and preserving the actual recovery steps.
Use the latest changelog entry to write a 75-word release announcement. Narrate it with Seed Speech TTS 2.0 in a pleased but restrained tone, and keep unsupported claims out of the script.
Review this project's Chinese and English welcome copy. Make one short mixed-language greeting with Seed Speech TTS 2.0 using a voice that supports mixing Chinese and English and automatic language handling.
Take the first paragraph of this project's tutorial and generate two readings with Seed Speech TTS 2.0: one neutral and one encouraging. Keep the spoken words identical and save both for review.
How to set up Seed Speech TTS 2.0 in Claude Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
This adds Spiral to the current project. Add --scope user to use it in every project.
claude mcp add --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start claude, type /mcp, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.
Use the Spiral skill
- Send Claude Code 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 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 Seed Speech TTS 2.0
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/bytedance/seed-speech/tts/v2", "input": { "text": "Hello, this is a test of ByteDance TTS 2.0 speech synthesis." } }'
Then paste one of the prompts above: Claude Code finds Seed Speech TTS 2.0 on Spiral, shows the price and runs it.
Seed Speech TTS 2.0 providers and prices
Spiral runs Seed Speech TTS 2.0 through fal. Open a card for today's price, with every fee included.
$0.039 per 1,000 characters of text. Rounded up to the next 1,000 characters, minimum 1,000.
Settings you can ask for
Seed Speech TTS 2.0 works from your text. Ask Claude Code for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Voice | vivi_mixed_en_zh_ja_es_id, mindy_en_es_id_pt_zh, stokie_en, dacey_en, tim_en, kian_en_zh, cedric_en_zh, sophie_en_zh and 33 more | stokie_en | Voice to use for synthesis. The preset name encodes the voice and its supported language codes. 'mixed_en_zh' means the voice can seamlessly blend English and Chinese; separate codes (e.g. 'en_zh') mean the voice supports each language independently. |
| Output format | mp3 or opus | mp3 | Output audio format. 'mp3' returns MP3 audio; 'opus' returns Opus audio in an Ogg container. |
| Sample rate | 8000, 16000, 22050, 24000, 32000, 44100, or 48000 | 24000 | Sample rate of the output audio in Hz. |
| Speed | 0.5 to 2 | 1 | Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed. |
| Volume | 0.5 to 2 | 1 | Volume. 1.0 is normal volume, 0.5 is half, 2.0 is double. |
| Pitch | -12 to 12 | 0 | Voice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave. |
| Language | zh, en, ja, es-mx, id, pt-br, ko, it and 2 more | Force the text to be read as a single language, disabling automatic language detection. Leave unset for automatic detection (including seamless Chinese/English mixing on bilingual voices). Codes: zh (Chinese), en (English), ja (Japanese), es-mx (Mexican Spanish), id (Indonesian), pt-br (Brazilian Portuguese), ko (Korean), it (Italian), de (German), fr (French). |
Every API field of Bytedance Seed Speech Text to Speech is on its tool page: open its card above.
What can you do with Seed Speech TTS 2.0 in Claude Code?
Turn project documentation and interface copy into spoken walkthroughs and audio drafts. Use Seed Speech TTS 2.0 to audition delivery while reviewing the script alongside the source text.
Product walkthrough narration
Turn an approved walkthrough script into spoken instructions. Request a patient delivery for steps listeners need to follow.
Customer support responses
Read approved support replies in a calm, reassuring tone, especially when explaining a delay or a recovery step.
Spoken assistant answers
Give a text assistant a spoken response with delivery suited to the answer, such as restrained for a correction or cheerful for good news.
Chinese and English announcements
Narrate announcements that switch between Chinese and English using a voice that supports mixing both languages.
Daily audio briefings
Convert a short, checked daily summary into narration with a consistent voice and delivery instruction.
Character dialogue drafts
Generate separate readings of scripted lines with different emotional directions to audition how a scene sounds.
Training lesson narration
Read lesson scripts in short passages with an unhurried delivery. Review the readings before adding them to a course.
More on Seed Speech TTS 2.0 and Claude Code
Overview
Seed Speech TTS 2.0 in other agents
Questions about Seed Speech TTS 2.0 in Claude Code
Can Claude Code use Seed Speech TTS 2.0?
Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run Seed Speech TTS 2.0 like any built-in tool.
How much does Seed Speech TTS 2.0 cost in Claude Code?
Each item in `text` adds $0.039. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude Code plan is separate.
Do I need a fal account to use Seed Speech TTS 2.0 in Claude Code?
No. Spiral runs Seed Speech TTS 2.0 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Seed Speech TTS 2.0 in Claude Code?
About two minutes: add the hosted server, then sign in.
Does Claude Code wait while Seed Speech TTS 2.0 runs?
Seed Speech TTS 2.0 runs in the background. Claude Code starts the run, checks on it and gives you the audio when it's ready.
What is Seed Speech TTS 2.0 useful for?
Use it to narrate explainers, speak assistant replies, or produce customer support messages. Its delivery instructions let you request a tone that fits the script.
How should I describe the delivery?
Keep the spoken script separate from directions such as “calm and reassuring” or “cheerful, with an unhurried pace.” Put those directions in the delivery instruction so they are not read aloud.
Can Seed Speech TTS 2.0 read Chinese and English in one script?
Yes, with a voice that supports mixing Chinese and English. Use automatic language handling for the mixed script rather than forcing one language.
Why might a multilingual script fail?
Multilingual support depends on the selected voice. Check that the voice supports the language in your script; a language mismatch can cause generation to fail.
How should I handle a long narration?
Split it into shorter passages if it exceeds the accepted text length. Keeping the same voice and delivery instruction across passages is a practical way to organize the narration.
Start using Seed Speech TTS 2.0 in Claude Code
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude Code:
set up https://spiral.ai/SKILL.md


