MCP / Models / Voice, music and sound

Seed Audio 1.0 MCP: audio from one text prompt

Seed Audio 1.0 makes audio from a text prompt, in a preset voice or guided by up to three reference clips or a picture. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

No API keyfrom $0.0375 / runText to speechByteDanceCommercial use
Seed Audio 1.0 sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Seed Audio 1.0 in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/bytedance-seed-audio-1-0.md. Help me connect the FlyMy.AI MCP to this assistant, then run Seed Audio 1.0 (flymyai/bytedance-seed-audio-1_0) for this task: Read this paragraph aloud with Seed Audio 1.0 in a calm, friendly voice and send me the audio file.
Open FlyMy.AIDownload brief

What Seed Audio 1.0 does

Write the text to say, or describe the audio to make, in prompt, required, up to 1,000 characters: it is not limited to reading a text aloud. voice picks a preset voice by name (the letters after the name are the languages it speaks, such as stokie_en or kian_en_zh). audios takes up to three reference clips, each up to 30 seconds and 10 MB (WAV, MP3, PCM or Ogg Opus), that you point to in the prompt as @Audio1, @Audio2 and @Audio3; image is a reference picture of up to 10 MB (JPEG, PNG or WebP) and cannot be sent with audio clips. speed (0.5 to 2), pitch (-12 to 12 semitones) and volume (0.5 to 2) shape the delivery, multilingual suits non-English or mixed-language text and output_format is mp3 (the default), wav or ogg_opus. Outputs: audio and duration, its length in seconds. You do not set the length: it follows the text and the speed.

It is billed on what the run uses, by the minutes of audio made. The price shown before the run is held on your balance and is worked out from the length of the prompt at a slow pace that suits speech, so a description of a scene can make longer audio than its length suggests (the model refuses audio that is too long); you are charged what the run cost. It makes one audio per request, makes no music and does not take a cloned-voice id.

Use a real person's voice or photo as a reference only with their consent.

Seed Audio 1.0 inputs

Every input of flymyai/bytedance-seed-audio-1_0 as its live schema lists them. Returns audio (array), duration (string).

InputType, values and default
# prompt
string required The text to say, or a description of the audio to make, up to 1,000 characters; point to reference clips as @Audio1, @Audio2 and @Audio3. $0.1875 per minute of audio made
# voice
string optional A preset voice name; the letters after the name are the languages it speaks. Names: stokie_en, vivi_mixed_en_zh_ja_es_id, mindy_en_es_id_pt_zh, kian_en_zh, cedric_en_zh, sophie_en_zh, jean_en_zh, magnus_en_zh, mabel_en_zh, nadia_en_zh, opal_en_zh, pearl_en_zh, quentin_en_zh, corinne_mixed_en_zh, esther_mixed_en_zh, lyla_mixed_en_zh, tracy_es_zh, sandy_es_mixed_en_zh, felix_zh, celeste_zh, monkey_king_zh. Left out, the model chooses
# audios
string optional Up to three reference audio clips, links or uploads, each up to 30 seconds and 10 MB (WAV, MP3, PCM or Ogg Opus), referred to in the prompt as @Audio1, @Audio2 and @Audio3; not together with image. Use a real person's voice only with their permission
# image
file optional Allowed: image file, as a URL or upload A reference picture (JPEG, PNG or WebP, up to 10 MB), a link or an upload; not together with audios. Use a real person's photo only with their permission
# speed
number optional Allowed: 0.5 to 2 Default: 1 Speech speed, 0.5-2 (1 is normal); a slower speed makes a longer audio
# pitch
integer optional Allowed: -12 to 12 Default: 0 Pitch shift in semitones, -12 to 12 (0 is normal; -12 is an octave lower)
# volume
number optional Allowed: 0.5 to 2 Default: 1 Volume, 0.5-2 (1 is normal)
# multilingual
boolean optional Default: false Use the multilingual variant of the model, which handles non-English and mixed-language text better
# output_format
string optional Allowed: mp3, wav, ogg_opus Default: mp3 File format: mp3 (the default), wav or ogg_opus

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Read this paragraph aloud with Seed Audio 1.0 in a calm, friendly voice and send me the audio file.”runs flymyai/bytedance-seed-audio-1_0
“Voice my product demo script with Seed Audio 1.0 a little slower and lower in pitch, and give me the audio file.”runs flymyai/bytedance-seed-audio-1_0
“Use Seed Audio 1.0 to say a line in the voice of the clip I attach, which is a recording of me.”runs flymyai/bytedance-seed-audio-1_0

Seed Audio 1.0 price

From $0.0375 per run, depending on prompt and speed. A run at the default settings costs $0.0975. A run costs $0.0375 to $0.195, depending on prompt and speed. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

Call Seed Audio 1.0 from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/bytedance-seed-audio-1_0",
  "input": {
    "prompt": "Welcome to FlyMy.AI. Your order has shipped and arrives on Friday."
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/bytedance-seed-audio-1_0/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/bytedance-seed-audio-1_0/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Welcome to FlyMy.AI. Your order has shipped and arrives on Friday.'

Questions about Seed Audio 1.0

Do I need a ByteDance API key for Seed Audio 1.0?

No. Seed Audio 1.0 runs on FlyMy.AI's account, so you need no ByteDance key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Seed Audio 1.0 cost?

From $0.0375 per run, depending on prompt and speed. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

How do I use Seed Audio 1.0 in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Read this paragraph aloud with Seed Audio 1.0 in a calm, friendly voice and send me the audio file." Your agent reads the inputs with get_model_schema and runs flymyai/bytedance-seed-audio-1_0 with run_model.

What does Seed Audio 1.0 need as input?

Seed Audio 1.0 requires prompt; it also takes 8 optional inputs, each listed on this page with its allowed values and default.

Can I call Seed Audio 1.0 from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/bytedance-seed-audio-1_0/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.